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. 23872
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or identity

    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
    373
    +0.16
    0.8%
    481
    +0.14
    0.6%
    614
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    673
    +0.16
    0.04
    614
    +0.14
    0.03
    569
    +0.10
    0.03
    Negative Logits
    uum
    -0.75
     defeats
    -0.68
     illnesses
    -0.67
     harms
    -0.67
    verett
    -0.65
    ptoms
    -0.65
     meanings
    -0.62
    isy
    -0.62
    ients
    -0.62
     reasons
    -0.62
    POSITIVE LOGITS
     undoubtedly
    0.97
     definitely
    0.82
    ometric
    0.82
     indeed
    0.81
     probably
    0.79
    ovie
    0.78
     yours
    0.76
     called
    0.73
     actually
    0.73
     Solitaire
    0.72
    Activations Density 0.114%

    No Known Activations