© 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. 11-RES-JB
    11. 20892
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly associated with political or sports backgrounds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various formerly prominent individuals and institutions

    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
     Retrieved
    -0.70
     unlike
    -0.66
    rained
    -0.65
    2018
    -0.64
    kson
    -0.64
    ologically
    -0.63
    morrow
    -0.62
    expected
    -0.62
    rosc
    -0.60
    alone
    -0.59
    POSITIVE LOGITS
     staffer
    1.15
     employee
    0.97
     contestant
    0.93
     accountant
    0.91
     assistant
    0.91
     operative
    0.88
     deputy
    0.88
     chief
    0.87
     prosecutor
    0.87
     standout
    0.86
    Activations Density 0.125%

    No Known Activations