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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22886
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    oai_token-act-pair · gpt-3.5-turbo

    HTML or markup elements 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
    ãĥ£
    -0.78
     Beir
    -0.68
     distribut
    -0.68
    ModLoader
    -0.65
     commissions
    -0.64
     administr
    -0.64
     bitters
    -0.63
     councils
    -0.63
     ratified
    -0.63
     equivalents
    -0.62
    POSITIVE LOGITS
    iframe
    1.29
    img
    1.27
    span
    1.12
    meta
    1.08
    insert
    1.07
    _>
    1.06
    embed
    1.02
    center
    1.02
    div
    1.01
    strong
    1.01
    Activations Density 0.019%

    No Known Activations