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. 21415
    Prev
    Next
    INDEX
    Explanations

    comparisons or mentions of comparisons

    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
    679
    +0.11
    0.5%
    276
    +0.10
    0.5%
    575
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.11
    0.02
    276
    +0.10
    0.02
    311
    +0.10
    0.01
    Negative Logits
    ignt
    -0.71
     havoc
    -0.67
    iscovery
    -0.67
    ighth
    -0.64
    ãĥİ
    -0.63
    nutrition
    -0.63
    oÄŁ
    -0.62
    ieri
    -0.62
    leasing
    -0.60
    zyme
    -0.60
    POSITIVE LOGITS
    xual
    0.87
     between
    0.87
    ogue
    0.86
     apples
    0.85
     favorably
    0.82
    isons
    0.79
     comparing
    0.78
     comparisons
    0.72
     thereto
    0.71
    rous
    0.70
    Activations Density 0.024%

    No Known Activations