© 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. 2632
    Prev
    Next
    INDEX
    Explanations

    images with captions

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

    references to images and their descriptions

    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
    -1.10
    ij士
    -1.09
     nodd
    -0.98
    everal
    -0.98
     oun
    -0.98
    ccording
    -0.97
     enthusi
    -0.97
    ò
    -0.95
    ntil
    -0.94
     therap
    -0.93
    POSITIVE LOGITS
     caption
    1.42
     copyright
    0.94
     Image
    0.67
     image
    0.63
     URL
    0.59
    Image
    0.57
     source
    0.57
     annotation
    0.56
     credit
    0.56
     Images
    0.56
    Activations Density 0.008%

    No Known Activations