© 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. 31373
    Prev
    Next
    INDEX
    Explanations

    words related to medical terms and research

    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
    554
    +0.13
    0.6%
    385
    +0.12
    0.5%
    404
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.18
    699
    +0.12
    0.04
    288
    +0.12
    0.18
    Negative Logits
     reckoning
    -0.84
     Peninsula
    -0.75
    ŃĶ
    -0.73
    ULT
    -0.72
    interrupted
    -0.72
    wcs
    -0.69
    living
    -0.69
    cffffcc
    -0.68
    temp
    -0.66
    «ĺ
    -0.66
    POSITIVE LOGITS
    ually
    1.19
    alia
    1.13
    entials
    1.09
    ilde
    1.06
    ieth
    1.01
    ullah
    1.00
    inyl
    0.95
    ifully
    0.95
    entially
    0.94
    uous
    0.94
    Activations Density 5.510%

    No Known Activations