© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 14797
    Prev
    Next
    INDEX
    Explanations

    words related to governance, governments, and authorities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "govern" and its related forms

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

    No Comments

    Negative Logits
     Dillon
    -0.68
     marrow
    -0.65
    rious
    -0.63
     Slov
    -0.62
     Survivors
    -0.61
     fraternity
    -0.58
    Bron
    -0.58
     chromosome
    -0.57
    working
    -0.56
     pree
    -0.55
    POSITIVE LOGITS
    govern
    0.97
    orship
    0.88
    iture
    0.85
    hart
    0.80
    Govern
    0.79
    esses
    0.79
    enstein
    0.77
    enges
    0.77
     ment
    0.75
    ments
    0.73
    Activations Density 0.010%

    No Known Activations