© 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 12288
    9. 8-RES_FS12288-JB
    11. 1173
    Prev
    Next
    INDEX
    Explanations

    words related to blood or medical conditions involving blood

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    314
    +0.11
    0.5%
    289
    +0.11
    0.5%
    26
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.11
    0.02
    26
    +0.11
    0.03
    85
    +0.11
    0.03
    Negative Logits
    awaru
    -0.94
     Amend
    -0.80
    IX
    -0.73
     VIDEOS
    -0.70
    ECH
    -0.70
    eering
    -0.69
    acle
    -0.68
    OPLE
    -0.68
    merce
    -0.67
    ATIONS
    -0.67
    POSITIVE LOGITS
    thirst
    1.42
    bath
    1.25
    hound
    1.23
    stained
    1.18
    lust
    1.10
    shed
    1.06
    lines
    0.98
     vessels
    0.97
     transf
    0.95
    spl
    0.88
    Activations Density 0.077%

    No Known Activations