© 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. 8-RES-JB
    11. 14833
    Prev
    Next
    INDEX
    Explanations

    terms related to government, law, ethics, and various authorities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental and societal functions

    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
    yss
    -0.82
    uitous
    -0.74
    icular
    -0.71
    iguous
    -0.69
    olini
    -0.68
    berries
    -0.68
    rupulous
    -0.67
    ouls
    -0.67
    pload
    -0.67
    adian
    -0.67
    POSITIVE LOGITS
     division
    1.15
     bureau
    1.03
     programme
    1.01
    mbudsman
    1.00
     newsletter
    0.96
     advisory
    0.96
     hotline
    0.95
     institute
    0.94
     department
    0.93
     cz
    0.91
    Activations Density 0.446%

    No Known Activations