© 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. 2595
    Prev
    Next
    INDEX
    Explanations

    references to media playback issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to media playback or its status

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     challeng
    -1.14
     predec
    -0.83
    everal
    -0.79
     seiz
    -0.79
     encount
    -0.78
     skelet
    -0.75
    ŃĶ
    -0.73
     pestic
    -0.72
     nodd
    -0.72
    ij士
    -0.71
    POSITIVE LOGITS
     is
    0.83
     coincides
    0.63
     exceeds
    0.61
     continues
    0.61
     exists
    0.60
     ceases
    0.60
     reflects
    0.57
     caption
    0.57
     remains
    0.57
     shows
    0.56
    Activations Density 0.002%

    No Known Activations