© 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. 10-RES-JB
    6. 18533
    Prev
    Next
    INDEX
    Explanations

    terms related to protests and demonstrations

    oai_token-act-pair · gpt-3.5-turbo

    instances of mass protests or demonstrations

    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
    CLASSIFIED
    -0.86
    poon
    -0.82
    venture
    -0.78
    ients
    -0.77
    worms
    -0.76
    worm
    -0.74
    idae
    -0.73
    cheat
    -0.71
    ãĥīãĥ©ãĤ´ãĥ³
    -0.71
    catentry
    -0.69
    POSITIVE LOGITS
     protest
    1.37
     rallies
    1.23
     streets
    1.23
     protesting
    1.20
     Protest
    1.18
     chanting
    1.18
     marches
    1.15
     protests
    1.13
     demonstrations
    1.12
     squares
    1.11
    Activations Density 0.286%

    No Known Activations