© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8285
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or criminal proceedings, investigations, and financial transactions involving different 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
    288
    +0.09
    0.5%
    649
    +0.08
    0.5%
    496
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.09
    0.03
    701
    +0.08
    0.02
    159
    +0.07
    0.02
    Negative Logits
    Region
    -0.51
    points
    -0.51
    Correct
    -0.50
    winner
    -0.48
    inki
    -0.48
    tti
    -0.48
    ============
    -0.47
     Poster
    -0.47
    ĪĴ
    -0.46
    Ô
    -0.46
    POSITIVE LOGITS
    retion
    0.64
    utive
    0.63
    utions
    0.60
    arcer
    0.60
    oyer
    0.59
    escent
    0.58
    ruciating
    0.58
    esse
    0.58
    imation
    0.58
    kefeller
    0.58
    Activations Density 0.194%

    No Known Activations