© 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. 31259
    Prev
    Next
    INDEX
    Explanations

    actions or potential outcomes in a situation

    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
    +0.18
    0.8%
    393
    +0.17
    0.7%
    418
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.18
    0.17
    393
    +0.17
    0.23
    297
    +0.13
    0.12
    Negative Logits
    rones
    -0.76
     Rab
    -0.76
     Notting
    -0.69
     Kamp
    -0.67
     Blitz
    -0.66
     1922
    -0.66
    ablishment
    -0.64
     Rus
    -0.64
     Kub
    -0.63
    phabet
    -0.62
    POSITIVE LOGITS
     easily
    1.03
     seen
    1.02
     viewed
    1.01
     likened
    1.00
     traced
    1.00
    acons
    1.00
     forgiven
    0.94
     construed
    0.93
     considered
    0.91
     undone
    0.90
    Activations Density 10.839%

    No Known Activations