© 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. 37194
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical actions or states

    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
    +0.24
    1.0%
    481
    +0.16
    0.7%
    721
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.24
    0.10
    665
    +0.16
    0.22
    283
    +0.11
    0.00
    Negative Logits
    ELS
    -0.73
    thodox
    -0.72
    indust
    -0.67
    Il
    -0.66
     Annex
    -0.65
    Eastern
    -0.64
     Reconstruction
    -0.60
     Promotion
    -0.60
     Lic
    -0.59
    drivers
    -0.59
    POSITIVE LOGITS
     yourself
    1.51
     yourselves
    1.31
     Yourself
    1.00
     your
    0.95
    poke
    0.89
     YOUR
    0.84
    your
    0.71
     smack
    0.70
    Your
    0.70
     shower
    0.69
    Activations Density 25.141%

    No Known Activations