© 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. 14051
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals in various contexts, possibly related to a public or political discourse

    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
    +0.22
    0.8%
    540
    +0.16
    0.6%
    274
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.22
    0.13
    274
    +0.16
    0.09
    679
    +0.15
    0.11
    Negative Logits
    ccording
    -0.95
    axy
    -0.92
    MpServer
    -0.90
    rafted
    -0.90
    PG
    -0.88
    bid
    -0.87
    rys
    -0.87
    ilation
    -0.86
    ILD
    -0.86
    osponsors
    -0.85
    POSITIVE LOGITS
     aloud
    1.09
     uttered
    1.08
     statements
    1.04
     regarding
    1.00
    gow
    0.96
    ariat
    0.92
    holders
    0.91
     about
    0.86
     concerning
    0.86
     publicly
    0.86
    Activations Density 1.705%

    No Known Activations