© 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. 10468
    Prev
    Next
    INDEX
    Explanations

    references to various aspects of bathing

    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
    35
    +0.15
    0.6%
    288
    +0.14
    0.5%
    420
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.13
    326
    +0.14
    0.10
    35
    +0.13
    0.06
    Negative Logits
    seless
    -0.90
     Gemini
    -0.88
    itars
    -0.83
     Uruguay
    -0.82
     Reaper
    -0.78
    perse
    -0.78
    aurus
    -0.77
    xxxx
    -0.75
    Document
    -0.74
     Grizzlies
    -0.72
    POSITIVE LOGITS
    tub
    1.89
    urst
    1.51
     ashore
    1.20
     salts
    1.19
    robe
    1.11
    maid
    1.09
    attery
    1.07
    creen
    1.05
    istry
    1.00
    ton
    0.95
    Activations Density 1.670%

    No Known Activations