© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 4906
    Prev
    Next
    INDEX
    Explanations

    dates in the format month day, year

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    numerical data or references to dates and times

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    398
    -0.66
    esc
    -0.66
     Escape
    -0.66
    âĨ
    -0.65
    358
    -0.64
     Tos
    -0.64
     Ler
    -0.64
    çĭ
    -0.63
     Severus
    -0.63
     Suc
    -0.62
    POSITIVE LOGITS
     Williamson
    0.79
     51
    0.76
     1921
    0.76
     21
    0.75
     1951
    0.73
    21
    0.73
    51
    0.72
    onds
    0.72
    odd
    0.71
     41
    0.71
    Activations Density 0.963%

    No Known Activations