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. 26382
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Robin."

    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
    288
    +0.11
    0.5%
    167
    +0.10
    0.5%
    356
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.11
    0.01
    356
    +0.10
    0.01
    574
    +0.10
    0.01
    Negative Logits
    mble
    -0.87
    resso
    -0.83
    xual
    -0.77
    ormons
    -0.75
    chnology
    -0.72
    pora
    -0.72
    aeda
    -0.71
    ormon
    -0.70
    ĵĺ
    -0.66
    definition
    -0.66
    POSITIVE LOGITS
     Hood
    1.30
    ette
    1.02
     Williams
    0.90
    alties
    0.85
     Hanson
    0.84
    istics
    0.81
    aldo
    0.81
     Hob
    0.78
    ettes
    0.77
    hood
    0.74
    Activations Density 0.004%

    No Known Activations