© 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 Local
    9. 6-RES_SCL-AJT
    11. 37123
    Prev
    Next
    INDEX
    Explanations

    URLs containing the string "www"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.20
    0.7%
    311
    +0.16
    0.6%
    385
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.20
    -0.01
    176
    +0.16
    0.05
    334
    +0.15
    0.04
    Negative Logits
    rained
    -0.87
     Courage
    -0.80
     Ballard
    -0.77
    IELD
    -0.74
     Pearce
    -0.73
     Manifest
    -0.73
     Pru
    -0.73
    abal
    -0.72
     Bots
    -0.71
     Moody
    -0.70
    POSITIVE LOGITS
    www
    1.50
    natureconservancy
    1.17
    ww
    1.09
    ibaba
    1.08
    youtube
    1.01
     www
    1.01
    ://
    0.98
    forums
    0.96
    hr
    0.96
    docs
    0.96
    Activations Density 6.234%

    No Known Activations