© 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 EvalsExportsinterp-engineNEWAPI 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. 20827
    Prev
    Next
    INDEX
    Explanations

    phrases related to political gatherings or speeches

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people, particularly crowds and audiences

    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
    iasis
    -0.74
    Leaks
    -0.63
    alin
    -0.60
     workaround
    -0.60
    Done
    -0.59
    erenn
    -0.59
     canonical
    -0.59
    QL
    -0.58
    agate
    -0.58
     recursive
    -0.57
    POSITIVE LOGITS
     cheering
    1.25
     chanting
    1.16
     cheers
    1.11
     chanted
    1.09
     applause
    1.09
     chants
    1.06
     cheered
    1.06
     applaud
    1.05
     gathered
    1.04
     assembled
    1.00
    Activations Density 0.154%

    No Known Activations