© 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. 10-RES-JB
    11. 11630
    Prev
    Next
    INDEX
    Explanations

    phrases related to voting and electoral processes

    oai_token-act-pair · gpt-3.5-turbo

    references to voting and electoral participation

    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
    Ĥª
    -0.81
    pps
    -0.80
    bal
    -0.74
    ounty
    -0.72
    olog
    -0.71
    ifier
    -0.69
    ãģ¯
    -0.68
    aneous
    -0.67
    ethe
    -0.67
    assad
    -0.66
    POSITIVE LOGITS
     habits
    1.32
     styles
    1.00
    redients
    0.99
     prowess
    0.97
     patterns
    0.97
     ability
    0.96
    rights
    0.95
     spree
    0.95
     abilities
    0.94
     capabilities
    0.93
    Activations Density 0.209%

    No Known Activations