© 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. 3-RES-JB
    11. 1913
    Prev
    Next
    INDEX
    Explanations

    political terms related to the two major parties in the US - Democrats and Republicans

    oai_token-act-pair · gpt-3.5-turbo

    references to political party affiliations and voting behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zsche
    -0.80
     Atlantis
    -0.75
    raph
    -0.71
    chwitz
    -0.70
    ulia
    -0.70
    arna
    -0.69
     999
    -0.69
    obar
    -0.65
     Fields
    -0.65
    tics
    -0.65
    POSITIVE LOGITS
     senators
    0.97
     lawmakers
    0.86
     Legislature
    0.81
     legislators
    0.79
     legislative
    0.78
     Senators
    0.77
    Senate
    0.76
     recess
    0.76
     majorities
    0.75
    è£
    0.74
    Activations Density 0.215%

    No Known Activations