© 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. 19338
    Prev
    Next
    INDEX
    Explanations

    locations or names including the word "Marie"

    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
    238
    +0.13
    0.6%
    313
    +0.11
    0.5%
    682
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    682
    +0.13
    0.01
    313
    +0.11
    0.01
    659
    +0.11
    0.01
    Negative Logits
    oted
    -0.78
    ODUCT
    -0.78
    dfx
    -0.77
    iances
    -0.76
    oppable
    -0.76
    arta
    -0.76
    iction
    -0.73
    =-=-=-=-=-=-=-=-
    -0.72
    iating
    -0.72
    okin
    -0.71
    POSITIVE LOGITS
     Claire
    1.03
    lla
    0.98
     Slaughter
    0.90
     Marie
    0.87
     Louise
    0.85
    Anne
    0.80
    lette
    0.80
    Marie
    0.75
    BuyableInstoreAndOnline
    0.74
     Thatcher
    0.74
    Activations Density 0.016%

    No Known Activations