© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12626
    Prev
    Next
    INDEX
    Explanations

    file names and technical information typically found in computer programming code

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    103
    +0.08
    0.5%
    549
    +0.07
    0.4%
    606
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.08
    0.01
    284
    +0.07
    0.01
    681
    +0.07
    0.01
    Negative Logits
    Journal
    -0.56
     <+
    -0.50
    uity
    -0.50
    wives
    -0.49
    Foreign
    -0.49
    Buzz
    -0.48
     ank
    -0.47
     donors
    -0.47
     foreign
    -0.47
    posts
    -0.47
    POSITIVE LOGITS
    ãĥ¯ãĥ³
    0.70
    ãĤ¨ãĥ«
    0.67
    é»Ĵ
    0.61
     ILCS
    0.57
    ierre
    0.55
    ibaba
    0.55
     laundry
    0.54
    ãĤ¦ãĤ¹
    0.54
    åĬ
    0.54
     EDITION
    0.54
    Activations Density 0.002%

    No Known Activations