© 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. 2658
    Prev
    Next
    INDEX
    Explanations

    phrases related to social movements and activism, specifically focusing on the "Black Lives Matter" movement

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Black Lives Matter" movement

    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
    Roberts
    -0.71
     spelling
    -0.70
     externalToEVAOnly
    -0.68
    ripp
    -0.66
     cleaners
    -0.62
    sweet
    -0.61
    Äĩ
    -0.61
    »Ĵ
    -0.60
    cephal
    -0.60
    Cass
    -0.60
    POSITIVE LOGITS
     Matter
    1.78
     Matters
    1.39
    matter
    1.27
     Movement
    0.94
     MAT
    0.90
     matter
    0.89
     Lives
    0.88
    ives
    0.88
     Liberation
    0.87
     Against
    0.81
    Activations Density 0.031%

    No Known Activations