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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12309
    Prev
    Next
    INDEX
    Explanations

    information about notable individuals and their accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote career achievements or notable roles of individuals in the entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.78
    morrow
    -0.75
    orum
    -0.72
    react
    -0.69
    Url
    -0.68
    orsi
    -0.68
    insk
    -0.65
    Newsletter
    -0.63
    Report
    -0.63
    osaurus
    -0.62
    POSITIVE LOGITS
     stint
    1.25
     classics
    0.81
     roles
    0.78
     spanning
    0.76
     spans
    0.74
    ionage
    0.71
     aerospace
    0.71
    enture
    0.71
    earances
    0.70
    Ĥª
    0.70
    Activations Density 0.723%

    No Known Activations