© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35939
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations followed by mention of legislative or political actions, particularly related to marijuana laws

    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
    +0.32
    1.5%
    481
    +0.16
    0.8%
    219
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.32
    0.14
    757
    +0.16
    0.11
    232
    +0.11
    0.12
    Negative Logits
    rious
    -0.72
    umbnails
    -0.69
    hement
    -0.68
    bp
    -0.67
    eatures
    -0.63
    Cert
    -0.60
    rencies
    -0.59
    letes
    -0.58
    Rating
    -0.58
    agonists
    -0.58
    POSITIVE LOGITS
     countryside
    0.95
     airspace
    0.90
     vicinity
    0.88
     classrooms
    0.84
     jails
    0.77
     suburbs
    0.76
     Gardens
    0.76
     alone
    0.76
     illegally
    0.75
     Springs
    0.75
    Activations Density 11.815%

    No Known Activations