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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 522
    Prev
    Next
    INDEX
    Explanations

    content related to activism and social justice

    oai_token-act-pair · gpt-3.5-turbo

    discussions of race, gender, and social justice movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Premium
    -0.82
    Luck
    -0.77
     Admir
    -0.77
     gamb
    -0.76
     gambling
    -0.76
    hire
    -0.75
    Buyable
    -0.75
     betting
    -0.74
    ircraft
    -0.74
     Malfoy
    -0.73
    POSITIVE LOGITS
     queer
    1.71
     marginalized
    1.47
     Feminist
    1.41
     feminist
    1.40
     LGBTQ
    1.39
     intersection
    1.35
     feminism
    1.33
     activism
    1.33
     intersections
    1.22
     anarchist
    1.20
    Activations Density 0.927%

    No Known Activations