© 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 12288
    9. 8-RES_FS12288-JB
    11. 9764
    Prev
    Next
    INDEX
    Explanations

    proper nouns, likely names of people or places

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    314
    +0.12
    0.6%
    447
    +0.11
    0.5%
    744
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.06
    430
    +0.11
    0.06
    457
    +0.11
    0.04
    Negative Logits
     CFL
    -0.70
    geries
    -0.69
    iencies
    -0.66
     attachments
    -0.58
     Celest
    -0.56
    LEASE
    -0.56
     fossils
    -0.56
     bondage
    -0.54
     Kodi
    -0.54
    utherford
    -0.54
    POSITIVE LOGITS
     replied
    1.00
     exclaimed
    1.00
     remarked
    0.92
    said
    0.90
     said
    0.86
     joked
    0.86
    ONSORED
    0.82
    Said
    0.82
     (@
    0.82
     proverb
    0.81
    Activations Density 0.287%

    No Known Activations