© 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
    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. 5642
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and player statistics associated with football and baseball teams

    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
    484
    +0.20
    0.7%
    99
    +0.17
    0.6%
    718
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.12
    171
    +0.17
    0.08
    99
    +0.17
    0.08
    Negative Logits
    aries
    -1.02
    actic
    -1.02
    neys
    -1.01
    atories
    -0.91
    gm
    -0.90
    ogene
    -0.90
    chens
    -0.89
    roleum
    -0.88
    lda
    -0.85
    aneous
    -0.85
    POSITIVE LOGITS
     Falcons
    1.40
     Bulldogs
    1.34
     Braves
    1.23
     Hawks
    1.11
     Tech
    1.03
    iev
    0.94
    nect
    0.93
    keye
    0.91
    vernment
    0.90
    acs
    0.86
    Activations Density 1.842%

    No Known Activations