Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8339
    Prev
    Next
    INDEX
    Explanations

    references to comic books, series, and characters

    oai_token-act-pair · gpt-3.5-turbo

    references to comic book issues and characters

    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
    YouTube
    -0.92
    youtube
    -0.83
     Youtube
    -0.75
    Streamer
    -0.74
    twitch
    -0.73
     youtube
    -0.72
     YouTube
    -0.69
    uay
    -0.68
    ideos
    -0.66
    EStream
    -0.65
    POSITIVE LOGITS
    Issue
    1.31
     Issue
    1.31
     issue
    1.29
     reprint
    1.28
    issue
    1.26
     reprinted
    1.23
     paperback
    1.19
     Comics
    1.09
     solicit
    1.09
    Volume
    1.08
    Activations Density 0.340%

    No Known Activations