© 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. 31100
    Prev
    Next
    INDEX
    Explanations

    medical conditions and specific types of cancer

    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
    151
    +0.06
    0.7%
    119
    +0.06
    0.7%
    99
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.06
    0.24
    288
    +0.06
    0.23
    325
    +0.05
    0.10
    Negative Logits
    ICAN
    -0.32
    ICA
    -0.30
    framework
    -0.29
    ãģ®æ
    -0.28
     Aval
    -0.28
    arial
    -0.27
    aria
    -0.27
    ivia
    -0.27
    owan
    -0.27
    andel
    -0.27
    POSITIVE LOGITS
     motions
    0.30
    view
    0.29
     stewards
    0.28
    Pause
    0.28
    ensible
    0.28
    brow
    0.28
     compuls
    0.28
     strokes
    0.27
    hold
    0.27
    aviour
    0.27
    Activations Density 9.960%

    No Known Activations