© 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. 37100
    Prev
    Next
    INDEX
    Explanations

    comparative and analytical terms

    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
    218
    +0.12
    0.6%
    311
    +0.11
    0.5%
    616
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.26
    575
    +0.11
    0.16
    195
    +0.10
    -0.01
    Negative Logits
     DRAG
    -0.72
     Leopard
    -0.69
     Slug
    -0.67
     Moose
    -0.65
     Tycoon
    -0.65
    IELD
    -0.63
    DAQ
    -0.61
    waves
    -0.61
     guiActiveUnfocused
    -0.61
     Hits
    -0.60
    POSITIVE LOGITS
    atory
    1.22
    ative
    1.17
    atives
    1.07
    abulary
    1.01
    isons
    1.00
    ational
    0.97
    minist
    0.97
    ancy
    0.97
    atories
    0.97
    ancies
    0.95
    Activations Density 9.295%

    No Known Activations