© 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. 8-RES-JB
    11. 17622
    Prev
    Next
    INDEX
    Explanations

    names of politicians and positions in government

    oai_token-act-pair · gpt-3.5-turbo

    names and titles of political figures and council members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     worldwide
    -0.89
     humankind
    -0.79
     Worldwide
    -0.76
     superpower
    -0.76
     mankind
    -0.74
     global
    -0.74
    DragonMagazine
    -0.73
     theorists
    -0.73
     shipped
    -0.72
     psychologists
    -0.71
    POSITIVE LOGITS
     Elections
    1.29
     Vote
    1.26
     constituency
    1.22
     mayoral
    1.21
     Legislative
    1.20
     caucus
    1.19
     Votes
    1.17
    bernatorial
    1.16
     Voting
    1.16
     Voters
    1.15
    Activations Density 0.924%

    No Known Activations