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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 46124
    Prev
    Next
    INDEX
    Explanations

    the concept of conditions and requirements in various contexts

    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
    715
    +0.10
    0.4%
    268
    +0.09
    0.4%
    224
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.10
    0.02
    540
    +0.09
    0.02
    535
    +0.09
    0.01
    Negative Logits
    issance
    -0.84
    umbn
    -0.81
    raph
    -0.74
     Sutherland
    -0.72
    ollen
    -0.72
    regor
    -0.71
    vironment
    -0.70
    gil
    -0.70
    ilus
    -0.70
    icro
    -0.70
    POSITIVE LOGITS
     stip
    1.27
     clauses
    1.16
     ratification
    1.02
     guaranteeing
    1.00
     ratified
    0.97
     clause
    0.95
     guarantees
    0.95
     guarantee
    0.95
     confir
    0.89
     agreeing
    0.89
    Activations Density 0.042%

    No Known Activations