© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 9139
    Prev
    Next
    INDEX
    Explanations

    substances and medications, particularly those related to medical conditions and their effects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.26
    1.0%
    642
    +0.15
    0.6%
    561
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.26
    0.21
    575
    +0.15
    0.18
    762
    +0.14
    0.15
    Negative Logits
    awar
    -0.88
    udeb
    -0.86
    req
    -0.85
    keye
    -0.84
    arella
    -0.82
    bitious
    -0.81
    gres
    -0.80
    arak
    -0.80
    verting
    -0.78
    arb
    -0.77
    POSITIVE LOGITS
     resembling
    1.05
     therein
    0.93
    ively
    0.90
    arium
    0.87
    brates
    0.86
    uria
    0.84
     belonging
    0.83
     Tradable
    0.82
     inhab
    0.82
     objects
    0.81
    Activations Density 3.900%

    No Known Activations