© 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 24576
    9. 8-RES_FS24576-JB
    11. 19768
    Prev
    Next
    INDEX
    Explanations

    words related to physical bodily features and medical conditions, specifically those related to the chest area

    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
    421
    +0.12
    0.6%
    67
    +0.12
    0.5%
    211
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.12
    0.01
    421
    +0.12
    0.01
    211
    +0.11
    0.01
    Negative Logits
     Estate
    -0.76
     CLSID
    -0.76
     Settlement
    -0.71
    esan
    -0.71
     accur
    -0.69
    hew
    -0.67
     Defenders
    -0.65
    ECH
    -0.65
    ãģ¦
    -0.64
    afort
    -0.63
    POSITIVE LOGITS
    wark
    1.27
    rill
    1.02
    leted
    0.99
    ging
    0.95
    acan
    0.91
    usha
    0.91
    orescent
    0.91
    bul
    0.90
    itive
    0.88
    acies
    0.88
    Activations Density 0.015%

    No Known Activations