© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8838
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports matchups and competitions

    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
    283
    +0.02
    0.4%
    193
    +0.02
    0.4%
    63
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.02
    0.02
    686
    +0.02
    0.02
    85
    +0.02
    0.02
    Negative Logits
    raz
    -0.19
    rene
    -0.17
    ocl
    -0.15
    bed
    -0.15
    hook
    -0.15
    bnb
    -0.14
    walker
    -0.14
     clipping
    -0.14
    nered
    -0.14
     bed
    -0.14
    POSITIVE LOGITS
    against
    0.17
    ĨĴ
    0.16
     Against
    0.15
     waged
    0.15
     Impossible
    0.15
     against
    0.15
    âķIJâķIJ
    0.15
    evil
    0.15
     sexes
    0.15
    Us
    0.14
    Activations Density 0.097%

    No Known Activations