© 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. 11119
    Prev
    Next
    INDEX
    Explanations

    words related to voting

    oai_token-act-pair · gpt-3.5-turbo

    references to voting actions and related concepts

    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
    ĸļ
    -0.94
    ptoms
    -0.74
    OLOGY
    -0.74
    ologies
    -0.74
    ology
    -0.73
    iasis
    -0.73
    ciating
    -0.72
    ological
    -0.69
     Flavoring
    -0.66
    cms
    -0.66
    POSITIVE LOGITS
     Democrat
    0.97
     yes
    0.90
     booth
    0.90
     SNP
    0.89
     Libertarian
    0.87
     YES
    0.86
     Republican
    0.84
     ballots
    0.83
     Democratic
    0.82
     booths
    0.79
    Activations Density 0.035%

    No Known Activations