© 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. 9347
    Prev
    Next
    INDEX
    Explanations

    words related to illegal or unethical actions

    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
    447
    +0.11
    0.5%
    288
    +0.11
    0.5%
    575
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.07
    288
    +0.11
    0.07
    78
    +0.10
    0.05
    Negative Logits
     corridors
    -0.79
    itudes
    -0.79
    urches
    -0.76
     sects
    -0.74
     channels
    -0.74
     strains
    -0.74
     industries
    -0.72
     regions
    -0.71
     interfaces
    -0.71
     economies
    -0.71
    POSITIVE LOGITS
     somewhere
    0.90
     someday
    0.89
     anywhere
    0.83
     apiece
    0.81
     thats
    0.77
     beforehand
    0.77
    ogram
    0.77
     WITHOUT
    0.76
     halfway
    0.76
     resembling
    0.76
    Activations Density 0.353%

    No Known Activations