Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40128
    Prev
    Next
    INDEX
    Explanations

    information related to cannabis, marijuana legalization, decriminalization, and drug policy

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.25
    1.1%
    288
    +0.17
    0.7%
    461
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.25
    0.13
    461
    +0.17
    0.06
    665
    +0.14
    0.09
    Negative Logits
     Piece
    -0.79
     Stevenson
    -0.77
    hon
    -0.74
    Thom
    -0.74
    elong
    -0.74
    semble
    -0.72
    ãĥł
    -0.69
    vel
    -0.69
    echo
    -0.68
    aer
    -0.68
    POSITIVE LOGITS
     legalization
    1.23
     dispensaries
    1.03
    arijuana
    1.02
     marijuana
    0.95
     dispensary
    0.94
     cultivation
    0.94
     prohibition
    0.92
     metabolites
    0.85
     smuggling
    0.83
     trafficking
    0.83
    Activations Density 3.705%

    No Known Activations