© 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. 37186
    Prev
    Next
    INDEX
    Explanations

    locations and places

    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
    430
    +0.10
    0.6%
    447
    +0.10
    0.6%
    314
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.14
    659
    +0.10
    0.14
    288
    +0.09
    0.22
    Negative Logits
    ictions
    -0.61
    terday
    -0.57
    ERAL
    -0.53
     plague
    -0.52
    ¥ŀ
    -0.52
     checkout
    -0.51
    fecture
    -0.51
     sentence
    -0.51
    itably
    -0.49
     payday
    -0.49
    POSITIVE LOGITS
    Bank
    0.68
    dale
    0.68
     Wars
    0.64
     Breaker
    0.64
    Side
    0.63
    Wing
    0.63
     Point
    0.63
    Walk
    0.63
    Net
    0.62
    esville
    0.62
    Activations Density 8.551%

    No Known Activations