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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 32541
    Prev
    Next
    INDEX
    Explanations

    words related to American football, specifically focusing on offensive and defensive positions, plays, and strategies

    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
    +0.26
    1.1%
    288
    +0.12
    0.5%
    379
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.26
    0.09
    422
    +0.12
    0.06
    278
    +0.12
    0.05
    Negative Logits
    20439
    -0.98
    chell
    -0.95
     Solitaire
    -0.93
    etsk
    -0.86
    Deal
    -0.84
    aminer
    -0.84
    hyde
    -0.84
    ilk
    -0.81
    bourg
    -0.81
    iless
    -0.81
    POSITIVE LOGITS
     linemen
    1.24
     lineman
    1.17
     coordinator
    0.91
     rebounds
    0.86
    scill
    0.85
     offensive
    0.83
     coaches
    0.81
     firepower
    0.80
     coordin
    0.78
     rotation
    0.77
    Activations Density 4.607%

    No Known Activations