© 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. 39839
    Prev
    Next
    INDEX
    Explanations

    Python code patterns and function names related to mathematical operations

    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
    52
    +0.07
    0.5%
    203
    +0.06
    0.5%
    274
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.07
    0.12
    317
    +0.06
    0.14
    621
    +0.06
    0.14
    Negative Logits
    wagon
    -0.65
    ible
    -0.56
    ript
    -0.52
    daq
    -0.52
    ship
    -0.51
    watch
    -0.50
    entimes
    -0.49
    hip
    -0.49
    lington
    -0.49
    nect
    -0.49
    POSITIVE LOGITS
    >>>>>>>>
    0.78
    >>>>
    0.72
    >>>
    0.65
     >>>
    0.51
     Haram
    0.48
    ¬¼
    0.44
     Rican
    0.43
    inez
    0.43
     Dele
    0.43
     Prin
    0.42
    Activations Density 8.334%

    No Known Activations