© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9735
    Prev
    Next
    INDEX
    Explanations

    words related to marijuana

    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
    481
    +0.17
    0.8%
    288
    +0.14
    0.6%
    459
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.17
    0.04
    67
    +0.14
    0.03
    288
    +0.13
    0.03
    Negative Logits
     Stevenson
    -0.90
     Laurent
    -0.74
     Coul
    -0.69
     partName
    -0.68
     Hawks
    -0.68
     Rove
    -0.68
    ãĥł
    -0.68
     Worcester
    -0.66
    semble
    -0.66
     Phant
    -0.65
    POSITIVE LOGITS
     legalization
    1.25
     dispensaries
    1.17
    arijuana
    1.09
     dispensary
    1.09
     cultivation
    1.07
     marijuana
    1.01
     cannabis
    0.92
     prohibition
    0.92
     metabolites
    0.90
     intoxication
    0.88
    Activations Density 0.074%

    No Known Activations