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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 3072
    9. 8-RES_FS3072-JB
    11. 2978
    Prev
    Next
    INDEX
    Explanations

    links and calls to action within text documents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    604
    +0.13
    0.6%
    70
    +0.11
    0.5%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.13
    0.05
    70
    +0.11
    0.04
    273
    +0.10
    0.04
    Negative Logits
     Scotia
    -0.63
    venge
    -0.59
     Warsaw
    -0.58
    egal
    -0.58
    utive
    -0.57
     Berk
    -0.57
    velt
    -0.57
    nia
    -0.56
     Chancellor
    -0.56
     franc
    -0.55
    POSITIVE LOGITS
    lish
    0.82
    wheel
    0.75
    urized
    0.72
    ety
    0.71
    ablishment
    0.71
    irs
    0.70
    root
    0.70
    river
    0.69
    able
    0.69
    pad
    0.68
    Activations Density 0.395%

    No Known Activations