© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    examples or discussions of specific cases or incidents

    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
    156
    +0.08
    0.6%
    319
    +0.07
    0.5%
    591
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.08
    0.08
    29
    +0.07
    0.08
    123
    +0.06
    0.07
    Negative Logits
    ynt
    -0.52
    ISH
    -0.49
    emis
    -0.45
    Pg
    -0.44
    soever
    -0.44
    rily
    -0.44
    ieties
    -0.44
     vested
    -0.43
    NOW
    -0.43
     broom
    -0.43
    POSITIVE LOGITS
    clus
    0.50
     Favor
    0.50
     Honolulu
    0.48
     lieu
    0.48
     Hawaii
    0.48
    sit
    0.46
    otto
    0.46
     Mariners
    0.45
     Oakland
    0.45
     Kuala
    0.44
    Activations Density 0.592%

    No Known Activations