© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 24022
    Prev
    Next
    INDEX
    Explanations

    image captions

    oai_token-act-pair · gpt-3.5-turbo

    references to images and visuals in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    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_pre
    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
    ccording
    -0.83
    ij士
    -0.83
     oun
    -0.71
    ŃĶ
    -0.66
    ntil
    -0.66
     Antar
    -0.65
    everal
    -0.65
     nodd
    -0.64
     agre
    -0.64
     enthusi
    -0.63
    POSITIVE LOGITS
     caption
    1.55
     copyright
    1.00
     Image
    0.76
     annotation
    0.73
    Image
    0.73
     URL
    0.66
    file
    0.66
     Images
    0.66
     image
    0.65
     Gallery
    0.64
    Activations Density 0.015%

    No Known Activations