© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1644
    Prev
    Next
    INDEX
    Explanations

    web links or website-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    288
    +0.12
    0.5%
    21
    +0.10
    0.4%
    57
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.12
    0.01
    508
    +0.10
    0.01
    21
    +0.10
    0.01
    Negative Logits
    Interstitial
    -0.80
     headphones
    -0.65
     charism
    -0.61
    200000
    -0.59
     unfocusedRange
    -0.59
     neigh
    -0.57
     Cros
    -0.57
    iated
    -0.56
     Pact
    -0.56
     Gillespie
    -0.55
    POSITIVE LOGITS
    Leaks
    1.26
    wiki
    1.01
    hack
    0.92
    ipedia
    0.87
     Commons
    0.87
    ileaks
    0.84
    Comm
    0.75
    Wiki
    0.73
    lement
    0.71
    iciency
    0.71
    Activations Density 0.019%

    No Known Activations