© 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. 9-RES-JB
    11. 11306
    Prev
    Next
    INDEX
    Explanations

    political terms and references, particularly related to different political parties

    oai_token-act-pair · gpt-3.5-turbo

    references to bipartisan elements in political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.93
     routines
    -0.85
    Delivery
    -0.82
     voy
    -0.72
     visitation
    -0.72
    estyles
    -0.72
     detain
    -0.71
     catalog
    -0.71
     voyage
    -0.70
     catalogue
    -0.70
    POSITIVE LOGITS
     Liberals
    1.52
     Democrats
    1.52
    Democrats
    1.52
     Conservatives
    1.50
    Republicans
    1.46
     Republicans
    1.46
     Democrat
    1.44
     conservatives
    1.41
     Democratic
    1.41
    Conservative
    1.40
    Activations Density 0.342%

    No Known Activations