© 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. 13531
    Prev
    Next
    INDEX
    Explanations

    locations and activities related to community governance

    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
    453
    +0.11
    0.6%
    420
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.08
    288
    +0.10
    0.09
    121
    +0.10
    0.05
    Negative Logits
    hedral
    -0.88
    ivia
    -0.80
    ogene
    -0.78
    gdala
    -0.77
    alogue
    -0.76
    igslist
    -0.74
    anchester
    -0.73
    urity
    -0.73
    ãĥĪ
    -0.72
    milo
    -0.72
    POSITIVE LOGITS
    robe
    1.45
    hips
    0.85
    ages
    0.85
    lings
    0.80
    lock
    0.80
    age
    0.76
    lest
    0.76
    ens
    0.75
     ward
    0.75
    craft
    0.75
    Activations Density 1.170%

    No Known Activations