© 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. 11-RES-JB
    11. 22620
    Prev
    Next
    INDEX
    Explanations

    terms related to legislation and lawmaking

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative processes and formal governance structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Royale
    -0.84
     Valiant
    -0.73
     Mub
    -0.69
    ilon
    -0.67
     Infinite
    -0.64
    ãĤ¨ãĥ«
    -0.64
    PLIED
    -0.64
     Templ
    -0.61
    elsen
    -0.61
     Continuous
    -0.60
    POSITIVE LOGITS
     enacted
    0.96
     enact
    0.95
    atures
    0.95
     redist
    0.90
     adjourn
    0.89
    woman
    0.87
    arians
    0.84
     repealing
    0.81
     drafting
    0.81
     session
    0.81
    Activations Density 0.039%

    No Known Activations