© 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. 3168
    Prev
    Next
    INDEX
    Explanations

    words related to social issues and activism

    oai_token-act-pair · gpt-3.5-turbo

    discourse surrounding criticism and accountability in social movements

    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
    earchers
    -0.96
     Zurich
    -0.77
     refuel
    -0.74
    arbon
    -0.74
     successor
    -0.73
     forecast
    -0.73
     prepar
    -0.72
     cellar
    -0.70
    ircraft
    -0.70
    hiba
    -0.69
    POSITIVE LOGITS
     misogyny
    1.64
     misogyn
    1.64
     feminists
    1.62
     Feminist
    1.55
     feminism
    1.55
     Femin
    1.53
     shaming
    1.52
     sexist
    1.50
     slurs
    1.49
    femin
    1.47
    Activations Density 1.271%

    No Known Activations