© 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. 738
    Prev
    Next
    INDEX
    Explanations

    proper nouns, names, and 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_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
    699
    +0.11
    0.5%
    708
    +0.10
    0.4%
    606
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.15
    659
    +0.10
    0.12
    699
    +0.09
    0.08
    Negative Logits
    ually
    -0.82
    arians
    -0.80
    icably
    -0.79
    uality
    -0.74
    orer
    -0.70
    ivity
    -0.68
    arian
    -0.68
    ional
    -0.67
    ismo
    -0.67
    ciating
    -0.67
    POSITIVE LOGITS
    outube
    1.08
    nda
    1.00
    nergy
    1.00
    ield
    0.99
    mph
    0.96
    ng
    0.95
    lene
    0.94
    von
    0.93
    orkshire
    0.93
    enne
    0.90
    Activations Density 4.538%

    No Known Activations