© 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. 31110
    Prev
    Next
    INDEX
    Explanations

    text in an unknown language or encoding pattern

    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
    160
    +0.15
    0.6%
    503
    +0.15
    0.6%
    346
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.15
    0.11
    675
    +0.15
    0.12
    308
    +0.13
    0.08
    Negative Logits
    hof
    -0.97
    selage
    -0.94
    atis
    -0.89
    ĸļ
    -0.88
    abase
    -0.85
    onom
    -0.83
    orno
    -0.82
    ortmund
    -0.82
    urion
    -0.80
     largeDownload
    -0.80
    POSITIVE LOGITS
    dating
    1.12
    ban
    0.94
    stairs
    0.93
    coming
    0.91
    ward
    0.90
    ded
    0.88
    lishes
    0.86
    mit
    0.85
    bably
    0.82
    izoph
    0.82
    Activations Density 5.675%

    No Known Activations