© 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. 0-RES-JB
    11. 8212
    Prev
    Next
    INDEX
    Explanations

    terms related to democracy and political terminology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of democratic processes and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dunham
    -0.65
     looting
    -0.64
     Jackson
    -0.64
     range
    -0.63
     Booker
    -0.63
     venture
    -0.62
     Solo
    -0.61
     visibility
    -0.60
     circulation
    -0.60
     Clair
    -0.60
    POSITIVE LOGITS
    dem
    3.17
    common
    1.92
    doc
    1.45
    dot
    1.24
    demon
    1.14
    dash
    1.09
    dev
    1.01
    dos
    0.99
    des
    0.98
    tar
    0.98
    Activations Density 0.009%

    No Known Activations