© 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 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. 9-RES-JB
    11. 15919
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical entities, specifically referring to republics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Republic."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TERN
    -0.72
    ãĤ¤
    -0.69
    balls
    -0.68
    Oracle
    -0.68
    utils
    -0.65
    stem
    -0.63
     Cue
    -0.62
    Detect
    -0.61
    berger
    -0.60
    verts
    -0.56
    POSITIVE LOGITS
    onia
    0.90
    rats
    0.88
    ans
    0.86
     Republic
    0.85
    oslov
    0.85
    ation
    0.84
    Republic
    0.84
    naire
    0.84
    orian
    0.80
    acy
    0.79
    Activations Density 0.055%

    No Known Activations