© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    topics related to social and political issues, such as healthcare, climate science, community demographics, and policy regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to social justice issues and criticisms of governing policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usive
    -0.73
    formance
    -0.70
    ateurs
    -0.70
    Rate
    -0.69
    practice
    -0.68
    cin
    -0.66
    ouble
    -0.65
    orthy
    -0.64
    aken
    -0.63
    trap
    -0.63
    POSITIVE LOGITS
     pope
    0.92
     earthquakes
    0.81
     Yugoslavia
    0.81
     marriages
    0.79
     wars
    0.79
     mosques
    0.78
     casinos
    0.78
     volcan
    0.77
     environmentalists
    0.77
     Pope
    0.77
    Activations Density 1.019%

    No Known Activations