© 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. 7-RES-JB
    11. 4040
    Prev
    Next
    INDEX
    Explanations

    names of politicians and government officials along with their respective states or positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of U.S. senators and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pim
    -0.73
     DJs
    -0.73
     traffickers
    -0.73
     smugglers
    -0.72
     robbers
    -0.72
     therapists
    -0.70
     shoot
    -0.69
     graffiti
    -0.68
     tattoos
    -0.68
     runway
    -0.68
    POSITIVE LOGITS
     Democrat
    0.96
     Appropriations
    0.95
    Republican
    0.92
     Majority
    0.91
    itol
    0.89
     Senate
    0.89
     Republican
    0.87
    osponsors
    0.87
    Senate
    0.87
     majority
    0.86
    Activations Density 0.299%

    No Known Activations