© 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. 3-RES-JB
    11. 12590
    Prev
    Next
    INDEX
    Explanations

    mentions of headings and subheadings in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "header."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ormon
    -0.80
    ingly
    -0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.73
    isexual
    -0.72
    âĶģ
    -0.72
    yip
    -0.69
    ĵĺ
    -0.68
    cest
    -0.67
    enged
    -0.67
     resil
    -0.66
    POSITIVE LOGITS
     Observatory
    0.71
    illo
    0.69
     Illust
    0.69
     quotes
    0.63
    agraph
    0.62
     HM
    0.61
     Barclays
    0.60
     illustration
    0.59
    idences
    0.59
     doi
    0.58
    Activations Density 0.000%

    No Known Activations