© 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. 4-RES-JB
    11. 13498
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental or political bodies, specifically the word 'congress'

    oai_token-act-pair · gpt-3.5-turbo

    references to congress and related terminology

    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
     Adin
    -0.76
    othe
    -0.75
    asive
    -0.71
    MQ
    -0.70
    lethal
    -0.69
     Mechdragon
    -0.67
     srf
    -0.64
    isms
    -0.64
     Pwr
    -0.64
     Assistance
    -0.63
    POSITIVE LOGITS
    cles
    0.86
    nect
    0.85
    mble
    0.84
    ciating
    0.84
    itors
    0.83
     congress
    0.83
    rex
    0.83
    eers
    0.82
    cle
    0.81
    ktop
    0.75
    Activations Density 0.037%

    No Known Activations