© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 10871
    Prev
    Next
    INDEX
    Explanations

    statistics and descriptions related to sports games

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    238
    +0.19
    0.6%
    668
    +0.17
    0.5%
    260
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.19
    0.05
    412
    +0.17
    0.05
    260
    +0.15
    0.05
    Negative Logits
    izoph
    -1.14
    yip
    -1.12
    orum
    -1.11
    hai
    -1.10
    agents
    -1.07
    atel
    -1.04
    lear
    -1.03
    onym
    -0.98
    arthy
    -0.98
    edi
    -0.98
    POSITIVE LOGITS
     FG
    1.09
     turnovers
    1.04
    Ĥİ
    1.03
     overall
    1.02
    game
    1.02
    =~=~
    1.01
     Indianapolis
    1.00
     consecutive
    1.00
     tying
    0.99
     league
    0.99
    Activations Density 0.546%

    No Known Activations