© 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 49152
    9. 8-RES_FS49152-JB
    11. 41767
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical bodies of water

    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
    184
    +0.12
    0.6%
    288
    +0.11
    0.5%
    537
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.03
    547
    +0.11
    0.03
    288
    +0.11
    0.03
    Negative Logits
    Lear
    -0.86
    paren
    -0.77
     BALL
    -0.71
    cash
    -0.69
    ivas
    -0.69
    PDATE
    -0.68
    Young
    -0.68
    morrow
    -0.67
    onym
    -0.67
    utters
    -0.66
    POSITIVE LOGITS
     region
    1.09
     basin
    0.94
     footh
    0.93
     Territories
    0.89
     regions
    0.89
     coastline
    0.89
     Peninsula
    0.87
     Basin
    0.85
     peninsula
    0.85
     Observatory
    0.84
    Activations Density 0.060%

    No Known Activations