© 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. 37017
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets involving the creation and manipulation of elements in the Document Object Model (DOM)

    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
    555
    +0.12
    0.6%
    152
    +0.12
    0.6%
    699
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.20
    640
    +0.12
    0.17
    160
    +0.11
    0.14
    Negative Logits
    âĹ¼
    -0.77
     Rosenthal
    -0.72
    nown
    -0.71
     Engel
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.69
     Bach
    -0.67
    entimes
    -0.66
     Mechdragon
    -0.65
    aneers
    -0.64
     Nunes
    -0.63
    POSITIVE LOGITS
    Interstitial
    1.23
    MpServer
    1.04
    taboola
    0.98
    localhost
    0.80
    SELECT
    0.74
    -'
    0.74
    caster
    0.74
     ',
    0.74
    custom
    0.73
    external
    0.73
    Activations Density 7.503%

    No Known Activations