© 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. 7422
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities, particularly within the context of governmental bodies like the House of Commons

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "House of" followed by a designation (e.g., Commons, Lords, Representatives)

    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
     lax
    -0.74
     sourcing
    -0.70
    20439
    -0.69
     tendon
    -0.68
     timet
    -0.67
     eclipse
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
    stanbul
    -0.63
     stride
    -0.63
     sling
    -0.63
    POSITIVE LOGITS
     Representatives
    1.60
     Commons
    1.42
     Lords
    1.34
     Reps
    1.10
     Cards
    1.08
     Representative
    1.03
     Assembly
    1.02
     Saud
    0.99
    Represent
    0.97
    legates
    0.95
    Activations Density 0.030%

    No Known Activations