© 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. 31260
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and impediments

    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
    +0.12
    0.7%
    417
    +0.10
    0.6%
    247
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.12
    0.08
    362
    +0.10
    0.10
    566
    +0.09
    0.09
    Negative Logits
    ndra
    -0.61
    ann
    -0.58
    mont
    -0.57
    hare
    -0.57
    tom
    -0.55
    Tu
    -0.54
    Fly
    -0.53
    variable
    -0.51
    nas
    -0.51
    angs
    -0.50
    POSITIVE LOGITS
     obstruction
    0.84
     obstruct
    0.75
    ignt
    0.69
    structed
    0.67
    struction
    0.64
    acles
    0.63
    uments
    0.63
    ensibly
    0.60
    igent
    0.58
    ions
    0.57
    Activations Density 11.733%

    No Known Activations