© 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. 9043
    Prev
    Next
    INDEX
    Explanations

    words related to concepts of time and fate

    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
    347
    +0.17
    0.5%
    80
    +0.15
    0.5%
    76
    +0.15
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.15
    76
    +0.15
    0.09
    331
    +0.15
    0.09
    Negative Logits
    ramid
    -1.17
    iants
    -1.13
    otic
    -1.10
    ktop
    -1.09
    qqa
    -1.08
    ulate
    -1.06
    ystem
    -1.06
    paces
    -1.02
    artment
    -1.02
    emies
    -1.02
    POSITIVE LOGITS
     heals
    1.32
    arily
    1.28
     Incarn
    1.12
    ishly
    1.11
    fw
    1.03
     incarn
    1.02
     grants
    1.00
     forgot
    1.00
    makers
    0.99
    lessly
    0.99
    Activations Density 2.352%

    No Known Activations