© 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. 7227
    Prev
    Next
    INDEX
    Explanations

    information related to law enforcement activities and crime

    oai_token-act-pair · gpt-3.5-turbo

    expressions of negation, specifically the word "No"

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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
    616
    +0.19
    0.6%
    393
    +0.17
    0.5%
    273
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.19
    0.07
    376
    +0.17
    0.06
    241
    +0.14
    0.06
    Negative Logits
    rex
    -1.04
    iership
    -1.04
    ials
    -1.01
    romy
    -1.00
    rog
    -1.00
    assies
    -0.97
    ktop
    -0.93
    ijuana
    -0.92
    sth
    -0.92
     pron
    -0.92
    POSITIVE LOGITS
    xious
    1.48
    etheless
    1.36
     matter
    1.32
     doubt
    1.28
     indication
    1.27
    terday
    1.23
     kidding
    1.19
     conceivable
    1.19
     longer
    1.18
     wonder
    1.11
    Activations Density 0.847%

    No Known Activations