© 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. 10458
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    159
    +0.12
    0.5%
    679
    +0.12
    0.5%
    70
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.00
    323
    +0.12
    0.04
    358
    +0.12
    0.03
    Negative Logits
    oodle
    -0.86
    Dialogue
    -0.85
    manship
    -0.85
    Benz
    -0.79
     Chick
    -0.78
    ĸļ
    -0.76
     Dietary
    -0.75
     Cosponsors
    -0.75
    icles
    -0.73
    iesta
    -0.73
    POSITIVE LOGITS
    email
    1.07
    @
    0.85
    =]
    0.77
     url
    0.77
     protected
    0.77
    ]
    0.73
    info
    0.73
    URI
    0.73
    minus
    0.73
     link
    0.72
    Activations Density 0.420%

    No Known Activations