© 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. 18516
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in journalism, commentary, and activism

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles associated with media and entertainment figures

    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
     [];
    -0.75
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.72
    Request
    -0.71
    EStreamFrame
    -0.69
     conclud
    -0.68
    Translation
    -0.67
    ascript
    -0.65
    eworthy
    -0.65
     secondary
    -0.64
    Analysis
    -0.63
    POSITIVE LOGITS
     extraord
    1.27
     Seymour
    1.07
     Dennis
    1.05
     Glenn
    1.05
     Milo
    1.05
     Marion
    1.04
     Gloria
    1.03
     Tony
    1.03
     Larry
    1.02
     Bruce
    1.02
    Activations Density 0.153%

    No Known Activations