© 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. 37079
    Prev
    Next
    INDEX
    Explanations

    measurements involving units of weight or dimension

    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
    288
    +0.17
    0.9%
    314
    +0.11
    0.6%
    447
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.17
    -0.01
    597
    +0.11
    0.04
    644
    +0.10
    0.09
    Negative Logits
     yours
    -0.58
    Else
    -0.58
     Norn
    -0.56
     Bind
    -0.54
     LINK
    -0.53
     manifest
    -0.53
    lde
    -0.52
    KA
    -0.52
     eminent
    -0.52
    Reply
    -0.52
    POSITIVE LOGITS
    enium
    1.33
    imet
    1.23
    imeters
    1.06
    imeter
    1.02
    eries
    0.92
    ipl
    0.89
    inery
    0.88
    iard
    0.85
    mill
    0.83
    ennial
    0.82
    Activations Density 10.281%

    No Known Activations