© 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. 1562
    Prev
    Next
    INDEX
    Explanations

    words indicating criticism or problematic behavior among individuals

    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
    393
    +0.18
    0.6%
    188
    +0.16
    0.6%
    537
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.10
    598
    +0.16
    0.03
    267
    +0.15
    0.04
    Negative Logits
    ,'"
    -1.37
    ',"
    -1.26
    ,''
    -0.99
    ,'
    -0.97
    âĢ¦"
    -0.97
    !",
    -0.96
    ',
    -0.95
    '),
    -0.95
    biased
    -0.95
    ..."
    -0.95
    POSITIVE LOGITS
     quotes
    1.17
     echoed
    1.17
     quoted
    1.08
    xtap
    1.06
     referring
    1.06
     understatement
    1.05
     sarcast
    1.05
     paraph
    1.03
    APTER
    1.02
     Zimmer
    1.00
    Activations Density 1.513%

    No Known Activations