© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3581
    Prev
    Next
    INDEX
    Explanations

    mentions of the House of Representatives, particularly with a focus on legislation and political activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to governance and legislation within a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    -0.72
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
    20439
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.64
    stanbul
    -0.62
     timet
    -0.62
     slap
    -0.60
    éĥ
    -0.60
     eclipse
    -0.58
    ãĤ¼ãĤ¦ãĤ¹
    -0.58
    POSITIVE LOGITS
     Representatives
    1.51
     Commons
    1.25
     Lords
    1.11
     Reps
    1.09
     Correction
    1.02
     Representative
    1.02
     Cards
    1.02
     Saud
    0.94
     Represent
    0.90
     representatives
    0.89
    Activations Density 0.018%

    No Known Activations