© 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. 7430
    Prev
    Next
    INDEX
    Explanations

    statements expressing uncertainty or lack of certainty

    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
    617
    +0.10
    0.4%
    692
    +0.10
    0.4%
    567
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.10
    0.04
    705
    +0.10
    0.04
    178
    +0.10
    0.04
    Negative Logits
    tic
    -0.71
     Resist
    -0.70
    ranged
    -0.68
    cit
    -0.68
    ngth
    -0.65
     Dil
    -0.64
    Anti
    -0.60
    ctory
    -0.58
    bestos
    -0.58
     Failed
    -0.57
    POSITIVE LOGITS
     definitively
    1.15
     specifics
    1.08
     whether
    0.96
     exact
    0.96
     anymore
    0.94
     nor
    0.92
     exactly
    0.92
     conclusive
    0.91
     definitive
    0.90
     precise
    0.88
    Activations Density 0.176%

    No Known Activations