© 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. 12073
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and protests

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and controversies involving public protests

    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
    alys
    -0.86
     analyse
    -0.83
     civilisation
    -0.82
    Buyable
    -0.79
     ageing
    -0.78
     maths
    -0.77
     OECD
    -0.77
    £
    -0.77
    BBC
    -0.77
     analys
    -0.76
    POSITIVE LOGITS
     organizer
    1.54
     organizers
    1.48
     chants
    1.37
     chanted
    1.35
     chanting
    1.33
     protesters
    1.28
     protester
    1.26
     marched
    1.23
     protestors
    1.23
     vandal
    1.22
    Activations Density 0.683%

    No Known Activations