© 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. 7735
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political ideologies and social justice issues

    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
     Shards
    -0.94
     Rings
    -0.82
    ulla
    -0.79
    Sym
    -0.77
     bruises
    -0.76
    ciating
    -0.73
     piles
    -0.73
     Craw
    -0.72
    ãĥ¼ãĥ³
    -0.72
     Sparks
    -0.72
    POSITIVE LOGITS
     fundamentalist
    1.16
     libertarian
    1.12
     liberal
    1.12
     authoritarian
    1.11
     socialist
    1.10
    liberal
    1.09
     populist
    1.09
     totalitarian
    1.08
     egalitarian
    1.06
     progressive
    1.04
    Activations Density 0.250%

    No Known Activations