© 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 EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12270
    Prev
    Next
    INDEX
    Explanations

    information related to sports contracts and negotiations

    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
    524
    +0.15
    0.5%
    202
    +0.15
    0.5%
    725
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.15
    0.05
    493
    +0.15
    0.04
    657
    +0.14
    0.05
    Negative Logits
     Hast
    -1.23
     SEM
    -1.04
     Egg
    -1.03
    ymm
    -0.99
     Samar
    -0.99
     Hobby
    -0.98
    enth
    -0.97
     Tiff
    -0.93
     Ging
    -0.93
     Fiorina
    -0.93
    POSITIVE LOGITS
     waivers
    1.24
     dues
    1.23
     contract
    1.16
     injury
    1.12
    interstitial
    1.11
     indefinite
    1.11
     indefinitely
    1.07
    contract
    1.07
    è¡
    1.06
     salary
    1.06
    Activations Density 1.321%

    No Known Activations