© 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 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. 13586
    Prev
    Next
    INDEX
    Explanations

    mentions of protests

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "protest" in various contexts

    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
    illac
    -0.89
    lasses
    -0.78
    bilt
    -0.75
    eger
    -0.73
    nown
    -0.72
    sonian
    -0.71
    ewater
    -0.70
    efficients
    -0.68
    ECD
    -0.67
     Purg
    -0.65
    POSITIVE LOGITS
     against
    1.26
    against
    1.12
     marches
    1.06
     rallies
    0.99
     Against
    0.98
     encamp
    0.98
     march
    0.96
     rally
    0.94
     protest
    0.94
     protesting
    0.94
    Activations Density 0.072%

    No Known Activations