© 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. 11371
    Prev
    Next
    INDEX
    Explanations

    words related to politics, particularly in the context of gathering support from various groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to electoral support and political strategy

    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
    resp
    -0.69
     planner
    -0.67
    practice
    -0.63
    agate
    -0.63
     dere
    -0.63
     unexplained
    -0.62
     specialization
    -0.60
    idia
    -0.60
     reconstruct
    -0.59
    mentioned
    -0.59
    POSITIVE LOGITS
     voters
    1.37
     audiences
    1.14
     independents
    1.08
     constituencies
    1.06
     Voters
    1.05
     supporters
    1.05
     crowds
    1.04
     votes
    1.03
     electorate
    1.03
     conservatives
    1.02
    Activations Density 0.749%

    No Known Activations