© 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. 8946
    Prev
    Next
    INDEX
    Explanations

    questions followed by a suggestion or request for information

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    354
    +0.14
    0.6%
    761
    +0.13
    0.6%
    674
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.14
    0.08
    566
    +0.13
    0.07
    551
    +0.12
    0.07
    Negative Logits
     Prometheus
    -0.79
     Lobby
    -0.71
     Pearce
    -0.69
     Codex
    -0.68
     Lect
    -0.66
     Ezek
    -0.65
    REDACTED
    -0.65
     Incarn
    -0.64
    ãĤ½
    -0.64
     Nemesis
    -0.64
    POSITIVE LOGITS
    'll
    0.76
    oint
    0.72
    usha
    0.68
    oos
    0.68
     wanna
    0.67
    'd
    0.67
    leans
    0.65
    outher
    0.64
    si
    0.63
    Enlarge
    0.63
    Activations Density 0.840%

    No Known Activations