© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1402
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Feinstein," potentially related to news articles or discussions about a political figure

    oai_token-act-pair · gpt-3.5-turbo

    references to the political figure Dianne Feinstein

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hy
    -0.77
     navigation
    -0.76
     trades
    -0.68
     util
    -0.66
     routes
    -0.66
     Gospel
    -0.65
     fortune
    -0.65
     dest
    -0.64
     nav
    -0.64
     Meteor
    -0.63
    POSITIVE LOGITS
     Feinstein
    4.18
    instein
    1.82
     Grassley
    1.73
     Dianne
    1.72
     Fiorina
    1.71
     Lieberman
    1.33
     Schiff
    1.33
     Pelosi
    1.33
     Nunes
    1.31
     Clapper
    1.30
    Activations Density 0.023%

    No Known Activations