© 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. 22561
    Prev
    Next
    INDEX
    Explanations

    the letter "C" followed by a single digit (1 to 9) or a two-digit number (10)

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter 'C' associated with various entities or organizations

    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
     lur
    -0.64
     thanks
    -0.63
     Yamaha
    -0.62
     longer
    -0.62
     Shutterstock
    -0.61
     Flickr
    -0.61
     err
    -0.60
     upward
    -0.58
     Chero
    -0.58
     Tinder
    -0.58
    POSITIVE LOGITS
    URRENT
    1.32
    overed
    1.31
    rossover
    1.30
    actus
    1.28
    esar
    1.27
    heddar
    1.22
    auldron
    1.20
    ottage
    1.18
    ripp
    1.17
    redo
    1.17
    Activations Density 0.044%

    No Known Activations