© 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. 10-RES-JB
    11. 3013
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical entities, particularly the term "Republic"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Republic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Oracle
    -0.77
    balls
    -0.74
     Cue
    -0.68
    Bird
    -0.63
    TERN
    -0.62
    berger
    -0.61
     Panther
    -0.59
     Predator
    -0.59
    jay
    -0.58
    lder
    -0.58
    POSITIVE LOGITS
    Republic
    1.01
    rats
    0.99
     Republic
    0.96
    oslov
    0.95
    ation
    0.94
    ans
    0.91
    onia
    0.90
     republic
    0.89
    arat
    0.89
    acies
    0.88
    Activations Density 0.029%

    No Known Activations