© 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. 11698
    Prev
    Next
    INDEX
    Explanations

    phrases related to illegal activities, particularly forced labor, sex trafficking, drug trafficking, and smuggling

    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
    +0.16
    0.7%
    442
    +0.12
    0.6%
    733
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.10
    575
    +0.12
    0.07
    442
    +0.12
    0.05
    Negative Logits
    irements
    -0.72
    ĪĴ
    -0.69
    arios
    -0.69
    thur
    -0.68
    laus
    -0.67
    vation
    -0.65
    comes
    -0.64
    nect
    -0.64
     Yosemite
    -0.63
    #$
    -0.63
    POSITIVE LOGITS
     trafficking
    1.05
     Traff
    1.02
     traffickers
    0.75
     traff
    0.72
     synd
    0.71
    ographers
    0.70
     Victims
    0.70
     Predators
    0.69
    anski
    0.67
     Reloaded
    0.66
    Activations Density 0.890%

    No Known Activations