© 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. 32251
    Prev
    Next
    INDEX
    Explanations

    statistics and information related to baseball players and teams

    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
    316
    +0.12
    0.5%
    634
    +0.12
    0.5%
    10
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.22
    709
    +0.12
    0.13
    288
    +0.10
    0.20
    Negative Logits
    achusetts
    -0.87
    trak
    -0.86
    irtual
    -0.85
    atson
    -0.85
    ioned
    -0.83
    ancies
    -0.82
    isec
    -0.82
    iflower
    -0.82
    neau
    -0.82
    ipop
    -0.81
    POSITIVE LOGITS
     Doodle
    0.74
     Stadium
    0.71
     Nieto
    0.70
     Clicker
    0.66
    Tur
    0.65
    issance
    0.64
     Fen
    0.63
     Vide
    0.62
     cabinets
    0.62
    Buy
    0.61
    Activations Density 8.084%

    No Known Activations