Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24404
    Prev
    Next
    INDEX
    Explanations

    phrases related to radical social or political changes

    oai_token-act-pair · gpt-3.5-turbo

    references to revolutions, crises, and significant societal changes

    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
     Cosponsors
    -0.69
    helps
    -0.67
     upkeep
    -0.65
     Crate
    -0.64
     Dove
    -0.63
     Feather
    -0.60
     teammates
    -0.60
    ossip
    -0.59
     donate
    -0.59
    inventoryQuantity
    -0.58
    POSITIVE LOGITS
     wherein
    1.06
     whereby
    1.05
     engulf
    0.90
     characterized
    0.88
    aclysm
    0.86
     usher
    0.84
     driven
    0.82
     ushered
    0.81
     Capitalism
    0.80
     reminiscent
    0.78
    Activations Density 0.325%

    No Known Activations