© 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. 8021
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, regulations, or terms and conditions

    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
    388
    +0.09
    0.5%
    688
    +0.08
    0.5%
    343
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    624
    +0.09
    0.02
    239
    +0.08
    0.02
    421
    +0.08
    0.02
    Negative Logits
    tumblr
    -0.64
    MT
    -0.62
    GW
    -0.58
    eps
    -0.58
     coli
    -0.56
    MAP
    -0.54
    drive
    -0.54
    matter
    -0.53
    advertisement
    -0.53
    study
    -0.53
    POSITIVE LOGITS
     discretion
    0.94
     judgment
    0.65
     custody
    0.63
     retri
    0.59
    riger
    0.58
    zona
    0.56
    ÃĥÃĤ
    0.55
     judgement
    0.55
     recourse
    0.54
     absolute
    0.54
    Activations Density 0.176%

    No Known Activations