Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26252
    Prev
    Next
    INDEX
    Explanations

    emotional states conveyed through language

    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
    314
    +0.23
    1.1%
    442
    +0.14
    0.6%
    160
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.23
    0.08
    157
    +0.14
    0.08
    514
    +0.12
    0.07
    Negative Logits
     metic
    -0.82
     SPI
    -0.78
     societies
    -0.75
     mathemat
    -0.72
     democracy
    -0.72
     Gmail
    -0.71
     democracies
    -0.70
     Skydragon
    -0.69
     JPM
    -0.69
     deflation
    -0.69
    POSITIVE LOGITS
    d
    1.49
    t
    1.41
    ve
    1.29
    ten
    1.26
    s
    1.26
    te
    1.26
    tre
    1.25
    re
    1.20
    c
    1.20
    sed
    1.19
    Activations Density 0.220%

    No Known Activations