© 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. 19762
    Prev
    Next
    INDEX
    Explanations

    mentions of food and dietary substitutions

    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
    628
    +0.12
    0.6%
    373
    +0.12
    0.6%
    60
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    232
    +0.12
    0.04
    41
    +0.09
    0.03
    Negative Logits
    pants
    -0.65
    Reloaded
    -0.62
    DOWN
    -0.60
     gems
    -0.59
     Cance
    -0.59
     tunes
    -0.57
     goodbye
    -0.57
     praise
    -0.54
     deprived
    -0.53
     Nad
    -0.52
    POSITIVE LOGITS
    ching
    0.89
    eling
    0.88
    ither
    0.86
    kered
    0.85
    iss
    0.84
    ut
    0.84
    elling
    0.84
    umatic
    0.83
    iton
    0.81
    ith
    0.81
    Activations Density 0.084%

    No Known Activations