© 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. 7349
    Prev
    Next
    INDEX
    Explanations

    words related to social issues or controversial topics

    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
    401
    +0.12
    0.5%
    455
    +0.10
    0.4%
    160
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.12
    0.07
    401
    +0.10
    0.06
    160
    +0.09
    0.07
    Negative Logits
    !,
    -0.68
    zan
    -0.66
    poon
    -0.65
    !:
    -0.64
    ECA
    -0.63
    dit
    -0.63
    +.
    -0.62
    iolet
    -0.62
    ovember
    -0.61
    ccording
    -0.60
    POSITIVE LOGITS
     varies
    0.90
     arises
    0.89
     becomes
    0.85
     persists
    0.85
    iest
    0.83
     outweigh
    0.81
     remains
    0.81
     disappears
    0.80
     differs
    0.78
     is
    0.76
    Activations Density 0.328%

    No Known Activations