Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 21
    Prev
    Next
    INDEX
    Explanations

    requests for instruction or help

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    +0.35
    2.0%
    160
    +0.23
    1.2%
    442
    +0.19
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.35
    0.35
    160
    +0.23
    0.35
    107
    +0.19
    0.28
    Negative Logits
     sculpt
    -0.87
     frontline
    -0.80
     spitting
    -0.78
     fleeing
    -0.78
     casc
    -0.78
     covenant
    -0.77
     displacement
    -0.76
     tram
    -0.76
     nightly
    -0.76
     increasingly
    -0.76
    POSITIVE LOGITS
    Advertisements
    1.83
    Conclusion
    1.65
    References
    1.58
    Advertisement
    1.55
    If
    1.54
    Trivia
    1.53
    Related
    1.52
    What
    1.51
    Loading
    1.50
    Discussion
    1.49
    Activations Density 2.034%

    No Known Activations