© 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. 9906
    Prev
    Next
    INDEX
    Explanations

    You provided content that includes activations of different tokens related to a specific theme regarding a product or service

    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
    71
    +0.11
    0.5%
    540
    +0.10
    0.4%
    225
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.11
    0.03
    540
    +0.10
    0.03
    288
    +0.09
    0.03
    Negative Logits
    algia
    -0.77
    apest
    -0.76
    DERR
    -0.74
    alam
    -0.74
    STER
    -0.73
    artment
    -0.70
    roma
    -0.70
     Rasm
    -0.68
    vironment
    -0.68
    MAL
    -0.68
    POSITIVE LOGITS
     maj
    1.32
     exerted
    1.01
     Awakens
    0.99
     multiplier
    0.93
     force
    0.86
    fulness
    0.83
    ments
    0.78
    ivot
    0.78
    ps
    0.78
     multipl
    0.74
    Activations Density 0.087%

    No Known Activations