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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7766
    Prev
    Next
    INDEX
    Explanations

    text related to code or technical language

    oai_token-act-pair · gpt-3.5-turbo

    segments of text that reference specific lines or passages within a document

    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
    ecast
    -0.86
    BuyableInstoreAndOnline
    -0.77
    steam
    -0.76
    umers
    -0.72
    consumer
    -0.72
    asio
    -0.70
    stocks
    -0.69
    games
    -0.69
    tested
    -0.68
    wcsstore
    -0.68
    POSITIVE LOGITS
     paragraph
    1.88
     paragraphs
    1.71
     footnote
    1.56
    paragraph
    1.55
     quotation
    1.54
     sentence
    1.53
     subsection
    1.40
     quote
    1.39
     wording
    1.38
     subparagraph
    1.36
    Activations Density 0.432%

    No Known Activations