© 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. 10-RES-JB
    11. 20530
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures or events

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Muammar Gaddafi" and its variants

    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
     toile
    -0.75
     lodging
    -0.68
     questioning
    -0.67
    ©¶æ
    -0.59
    taboola
    -0.59
    ĪĴ
    -0.58
     CBI
    -0.58
     solicitation
    -0.56
     Vaugh
    -0.56
     Dull
    -0.55
    POSITIVE LOGITS
    intosh
    1.07
    ufact
    0.97
    arella
    0.87
    ONEY
    0.86
     Gaddafi
    0.81
    enzie
    0.81
    udi
    0.78
    tu
    0.78
    achine
    0.77
    angelo
    0.76
    Activations Density 0.320%

    No Known Activations