© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 45770
    Prev
    Next
    INDEX
    Explanations

    numerical representations of ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.24
    1.2%
    160
    +0.12
    0.6%
    442
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.24
    0.04
    442
    +0.12
    0.04
    160
    +0.12
    0.04
    Negative Logits
     scrap
    -0.86
     brid
    -0.79
    vertisement
    -0.78
     grap
    -0.75
     thrott
    -0.75
     paran
    -0.73
     honoured
    -0.72
     differe
    -0.72
     referen
    -0.70
     retard
    -0.70
    POSITIVE LOGITS
    Conclusion
    1.55
    CONCLUS
    1.30
    Advertisements
    1.28
    Finally
    1.27
    Lastly
    1.24
    ________________________________________________________________
    1.18
    Others
    1.18
    ________________________
    1.18
    --------------------------------------------------------
    1.16
    ----------------------------------------------------------------
    1.14
    Activations Density 0.049%

    No Known Activations