© 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. 8998
    Prev
    Next
    INDEX
    Explanations

    references to time or chronological order

    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
    267
    +0.15
    0.5%
    223
    +0.14
    0.5%
    373
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.15
    0.07
    458
    +0.14
    0.06
    706
    +0.11
    0.06
    Negative Logits
    angan
    -0.85
    Lago
    -0.83
    cil
    -0.81
    ollow
    -0.79
    entials
    -0.78
    abella
    -0.77
     Controls
    -0.77
    hare
    -0.75
    chool
    -0.74
    afort
    -0.74
    POSITIVE LOGITS
     ditch
    1.24
     gasp
    1.21
    ebin
    1.13
     decade
    1.12
     month
    1.09
     week
    1.08
     year
    1.04
     rites
    1.04
    fm
    0.99
     century
    0.97
    Activations Density 0.753%

    No Known Activations