© 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. 0-RES-JB
    11. 22330
    Prev
    Next
    INDEX
    Explanations

    references to political representatives, particularly with the title "Rep." and digits following it

    oai_token-act-pair · gpt-3.5-turbo

    references to representatives in a legislative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atonin
    -0.79
    âĹ¼
    -0.72
    ambling
    -0.72
     vertically
    -0.71
    GGGGGGGG
    -0.70
    onds
    -0.68
    football
    -0.66
    acre
    -0.65
    bowl
    -0.65
    basketball
    -0.62
    POSITIVE LOGITS
     Rep
    3.72
    Rep
    2.73
     Reps
    2.62
     Representative
    2.05
     Sen
    1.98
     Congressman
    1.75
    rep
    1.73
     rep
    1.58
     congressman
    1.56
    Sen
    1.52
    Activations Density 0.010%

    No Known Activations