© 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. 37219
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations or regions

    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
    359
    +0.13
    0.6%
    715
    +0.10
    0.4%
    689
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.13
    0.02
    232
    +0.10
    0.02
    556
    +0.10
    0.01
    Negative Logits
    iasco
    -0.82
     srfAttach
    -0.80
     constitu
    -0.72
    PDATE
    -0.72
    ocument
    -0.71
    ã
    -0.71
    natureconservancy
    -0.64
     tun
    -0.63
    ãĤ©
    -0.63
    ï¸ı
    -0.60
    POSITIVE LOGITS
    wick
    0.81
    bury
    0.78
    enment
    0.78
    west
    0.77
    West
    0.74
    church
    0.73
     Abbey
    0.72
    bia
    0.70
     Baptist
    0.69
    lake
    0.69
    Activations Density 0.038%

    No Known Activations