© 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. 37220
    Prev
    Next
    INDEX
    Explanations

    statements questioning or analyzing actions or motives of individuals or organizations

    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
    +0.14
    0.7%
    393
    +0.12
    0.6%
    581
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.29
    382
    +0.12
    0.10
    283
    +0.10
    0.02
    Negative Logits
    urers
    -0.66
    tails
    -0.62
     Delicious
    -0.58
    anity
    -0.56
     segregated
    -0.55
    abi
    -0.53
    ãĤº
    -0.52
     Recovery
    -0.50
    ãĥĵ
    -0.49
     Beasts
    -0.49
    POSITIVE LOGITS
     knows
    0.80
    pires
    0.77
     reads
    0.70
     wants
    0.68
    soever
    0.66
    lvl
    0.66
     cares
    0.64
     bothers
    0.63
     completes
    0.63
     remembers
    0.62
    Activations Density 12.064%

    No Known Activations