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. 12161
    Prev
    Next
    INDEX
    Explanations

    phrases related to news delivery and subscriptions

    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
    361
    +0.11
    0.5%
    306
    +0.10
    0.4%
    59
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.11
    0.01
    361
    +0.10
    0.01
    18
    +0.09
    0.01
    Negative Logits
    conn
    -0.78
    wikipedia
    -0.78
    perty
    -0.71
    é¾įå
    -0.67
     conce
    -0.62
    appropri
    -0.62
    bes
    -0.61
    tymology
    -0.59
    ItemTracker
    -0.58
     Geh
    -0.58
    POSITIVE LOGITS
    imentary
    0.91
     delivered
    0.83
    Interstitial
    0.76
     weekday
    0.75
    ragon
    0.72
     Emails
    0.71
     personalized
    0.70
     Subscribe
    0.70
    ocument
    0.67
    ivered
    0.67
    Activations Density 0.007%

    No Known Activations