© 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. 11-RES-JB
    11. 18564
    Prev
    Next
    INDEX
    Explanations

    events or gatherings where a large group of people participate or protest

    oai_token-act-pair · gpt-3.5-turbo

    large gatherings or protests involving significant numbers of people

    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
     relapse
    -0.71
     causation
    -0.67
    esson
    -0.61
     devs
    -0.60
    Detect
    -0.60
     defic
    -0.59
    thood
    -0.59
     operative
    -0.59
    retion
    -0.58
     matured
    -0.58
    POSITIVE LOGITS
     marches
    1.06
     chanting
    0.98
     marched
    0.97
     march
    0.96
     rallies
    0.92
     streets
    0.91
     peacefully
    0.90
     converge
    0.89
     gathered
    0.86
     Saturday
    0.85
    Activations Density 0.203%

    No Known Activations