© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33552
    Prev
    Next
    INDEX
    Explanations

    references to international conventions and technical reports related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    years and dates within the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.25
    1.3%
    481
    +0.18
    0.9%
    760
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.39
    739
    +0.18
    0.07
    314
    +0.10
    -0.10
    Negative Logits
     "@
    -0.66
     curtains
    -0.60
     outl
    -0.60
     pun
    -0.60
     lim
    -0.59
     fighters
    -0.58
     resemb
    -0.57
     crab
    -0.57
     forfe
    -0.55
     hairc
    -0.53
    POSITIVE LOGITS
     Retrieved
    0.82
     Includes
    0.79
    Reviewed
    0.77
    pdf
    0.76
     pdf
    0.73
    updated
    0.69
    Present
    0.69
     Ages
    0.68
     Appendix
    0.67
     Supplement
    0.66
    Activations Density 21.571%

    No Known Activations