© 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. 7280
    Prev
    Next
    INDEX
    Explanations

    recipes and food-related instructions

    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
    218
    +0.16
    0.7%
    736
    +0.12
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.16
    0.05
    354
    +0.12
    0.05
    566
    +0.10
    0.05
    Negative Logits
    SPONSORED
    -0.80
    Interview
    -0.65
    ivari
    -0.64
    ramer
    -0.63
     Adjusted
    -0.62
    adjusted
    -0.61
    toggle
    -0.60
    Minor
    -0.60
    uitous
    -0.60
    Missing
    -0.59
    POSITIVE LOGITS
    'll
    0.81
     WILL
    0.80
     promise
    0.78
     Promise
    0.74
    ngth
    0.71
     will
    0.70
     otherwise
    0.68
     safest
    0.67
     surely
    0.67
    ĸļ
    0.67
    Activations Density 0.375%

    No Known Activations