© 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. 5067
    Prev
    Next
    INDEX
    Explanations

    mentions of risky behaviors and medical data

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

    references to sexual activity and its associated behaviors or conditions

    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
    ĪĴ
    -0.82
    Ü
    -0.72
    aughs
    -0.64
    ©¶æ¥µ
    -0.61
    License
    -0.60
    billion
    -0.59
    munition
    -0.58
    Copyright
    -0.56
    redits
    -0.56
    iasm
    -0.56
    POSITIVE LOGITS
     thereafter
    0.99
     afterward
    0.96
     afterwards
    0.93
     immediately
    0.90
     AFTER
    0.90
     again
    0.89
     during
    0.89
     beforehand
    0.88
     sooner
    0.87
     initially
    0.86
    Activations Density 0.839%

    No Known Activations