© 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 768
    9. 8-RES_FS768-JB
    11. 760
    Prev
    Next
    INDEX
    Explanations

    phrases related to contracts or agreements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    709
    +0.14
    0.6%
    572
    +0.11
    0.5%
    311
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.14
    0.10
    8
    +0.11
    0.12
    709
    +0.11
    0.11
    Negative Logits
    "},"
    -0.60
     throats
    -0.60
    Sund
    -0.55
    prus
    -0.55
     bang
    -0.54
     \'
    -0.53
     basket
    -0.52
    chairs
    -0.52
     âĢİ
    -0.52
    CLOSE
    -0.52
    POSITIVE LOGITS
    ,
    0.93
    ,.
    0.92
    .,
    0.83
    ,,
    0.73
    terday
    0.72
    ,...
    0.71
    entimes
    0.67
     guiActiveUn
    0.65
    ,-
    0.65
    !,
    0.64
    Activations Density 3.573%

    No Known Activations