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

    Neuronpedia

    Jacobian LensNEW
    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. 10810
    Prev
    Next
    INDEX
    Explanations

    locations and events

    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
    481
    +0.30
    1.6%
    640
    +0.30
    1.5%
    447
    +0.20
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.30
    0.18
    160
    +0.30
    0.17
    442
    +0.20
    0.15
    Negative Logits
    ©¶æ
    -0.79
     deliber
    -0.78
     advoc
    -0.77
     bloc
    -0.77
     probation
    -0.76
     frontline
    -0.76
     favour
    -0.76
     baseline
    -0.76
     appoint
    -0.75
     suppression
    -0.74
    POSITIVE LOGITS
    Advertisement
    1.42
    Anyway
    1.24
    THE
    1.23
    Born
    1.23
    Advertisements
    1.23
    Located
    1.23
    Enlarge
    1.23
    Phot
    1.22
    advertisement
    1.19
    Imagine
    1.18
    Activations Density 0.578%

    No Known Activations