© 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. 7-RES-JB
    11. 12484
    Prev
    Next
    INDEX
    Explanations

    references to voting-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voting and voter rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ologically
    -0.80
     Palestin
    -0.77
    ously
    -0.73
    ĸļ
    -0.71
    ternally
    -0.71
     Flavoring
    -0.70
    obar
    -0.69
    ienne
    -0.68
    Else
    -0.68
     Bei
    -0.68
    POSITIVE LOGITS
     turnout
    0.99
    eering
    0.96
     irregularities
    0.93
     fraud
    0.86
     registration
    0.84
     booth
    0.83
     booths
    0.83
    ricting
    0.79
     machines
    0.78
     bloc
    0.78
    Activations Density 0.044%

    No Known Activations