© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41521
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    674
    +0.12
    0.5%
    243
    +0.09
    0.4%
    543
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.12
    0.03
    284
    +0.09
    0.03
    484
    +0.09
    0.03
    Negative Logits
     Representative
    -0.67
    FUL
    -0.66
    ummer
    -0.66
    SPONSORED
    -0.64
    STER
    -0.64
     Journalism
    -0.63
    termination
    -0.63
    SPA
    -0.63
     representative
    -0.62
    ĨĴ
    -0.62
    POSITIVE LOGITS
     mortar
    0.91
     conquer
    0.81
    Ń·
    0.80
     crochet
    0.76
     parcel
    0.76
     weave
    0.74
     pound
    0.73
     shove
    0.72
    rew
    0.72
     mash
    0.71
    Activations Density 0.072%

    No Known Activations