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 24576
    5. 8-RES_FS24576-JB
    6. 23406
    Prev
    Next
    INDEX
    Explanations

    clauses that introduce additional information or context about a subject

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.33
    1.6%
    480
    +0.28
    1.4%
    87
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.33
    0.03
    757
    +0.28
    0.03
    655
    +0.12
    0.03
    Negative Logits
     Vaugh
    -0.52
    GER
    -0.52
     Fol
    -0.52
    FN
    -0.51
     Seym
    -0.50
     Ott
    -0.50
    utable
    -0.49
    Sad
    -0.49
     Brus
    -0.49
     Gateway
    -0.49
    POSITIVE LOGITS
    zbollah
    0.72
     comprises
    0.69
    ;;;;;;;;;;;;
    0.65
    netflix
    0.63
     operates
    0.61
    Offline
    0.61
    iannopoulos
    0.61
     owns
    0.61
    psons
    0.60
    ojure
    0.60
    Activations Density 0.095%

    No Known Activations