© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    terms related to government, law, business, and healthcare

    oai_token-act-pair · gpt-3.5-turbo

    topics related to governance, law, and small businesses

    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
    ãĥ£
    -0.85
    bright
    -0.73
    ãĤ¨ãĥ«
    -0.71
    usky
    -0.70
    BUS
    -0.69
    Cry
    -0.69
    Hom
    -0.68
    wash
    -0.68
    thy
    -0.68
     Frie
    -0.68
    POSITIVE LOGITS
    edly
    0.88
     syndrome
    0.81
    eers
    0.77
     theorem
    0.75
     fallacy
    0.75
     equivalents
    0.74
     solutions
    0.73
     approaches
    0.71
     deployments
    0.71
     vig
    0.69
    Activations Density 0.464%

    No Known Activations