© 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. 8810
    Prev
    Next
    INDEX
    Explanations

    summaries or descriptions of entertainment media such as movies, TV shows, and sports events

    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
    447
    +0.29
    1.0%
    151
    +0.17
    0.6%
    481
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.29
    0.08
    640
    +0.17
    0.09
    23
    +0.15
    0.06
    Negative Logits
    aku
    -1.06
    acan
    -1.04
    £ı
    -1.02
    userc
    -0.97
     laun
    -0.96
    bered
    -0.96
    amiya
    -0.96
    ĸļ
    -0.94
    ¥µ
    -0.93
    urated
    -0.92
    POSITIVE LOGITS
     None
    1.03
     Starts
    0.90
     Winner
    0.90
     Yes
    0.90
     Compl
    0.89
     Unknown
    0.88
     Runs
    0.88
     Ramsay
    0.88
     Combine
    0.88
     Only
    0.87
    Activations Density 0.736%

    No Known Activations