© 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 24576
    9. 8-RES_FS24576-JB
    11. 7926
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    373
    +0.15
    0.7%
    544
    +0.11
    0.5%
    430
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.15
    0.08
    430
    +0.11
    0.08
    25
    +0.11
    0.05
    Negative Logits
    iture
    -0.67
    ="#
    -0.58
     pse
    -0.56
    benefit
    -0.56
    worldly
    -0.55
    vec
    -0.52
    htaking
    -0.51
     chimpan
    -0.49
    advertisement
    -0.49
     handwritten
    -0.49
    POSITIVE LOGITS
     onwards
    1.07
     onward
    0.96
     thereafter
    0.75
    rosso
    0.67
    .
    0.67
     additionally
    0.66
    ;
    0.61
     again
    0.61
     completes
    0.60
     Lastly
    0.59
    Activations Density 0.253%

    No Known Activations