© 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. 10-RES-JB
    11. 6670
    Prev
    Next
    INDEX
    Explanations

    terms related to political elections and ballot measures

    oai_token-act-pair · gpt-3.5-turbo

    references to ballots and ballot initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kut
    -0.80
    icago
    -0.80
    ews
    -0.68
    PLIED
    -0.68
     Flavoring
    -0.66
    hered
    -0.66
    ofi
    -0.65
    rir
    -0.65
    unct
    -0.64
     Emin
    -0.64
    POSITIVE LOGITS
     ballots
    1.05
     ballot
    1.03
     box
    1.01
    room
    1.00
    ination
    0.92
     canv
    0.90
    boxes
    0.87
     boxes
    0.86
     booth
    0.84
    box
    0.84
    Activations Density 0.025%

    No Known Activations