© 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. 3131
    Prev
    Next
    INDEX
    Explanations

    phrases related to education and government policies

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.15
    0.6%
    151
    +0.13
    0.6%
    725
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    725
    +0.15
    0.06
    101
    +0.13
    0.09
    195
    +0.13
    0.03
    Negative Logits
    heed
    -0.97
    quer
    -0.84
    icum
    -0.83
    cel
    -0.80
    ciating
    -0.80
    ccording
    -0.80
    etric
    -0.80
    atan
    -0.78
    til
    -0.78
     neighb
    -0.77
    POSITIVE LOGITS
     inconsistencies
    0.89
     how
    0.87
     prominently
    0.82
     noting
    0.81
    ered
    0.80
     notes
    0.80
     discrepancies
    0.79
     approving
    0.78
    uality
    0.77
     Twain
    0.75
    Activations Density 1.386%

    No Known Activations