© 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. 12-RES-JB
    11. 4571
    Prev
    Next
    INDEX
    Explanations

    names related to Islamic figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the name "Muammar" or similar variations, indicating a focus on the topic of Muammar Gaddafi

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     comparable
    -0.83
     similar
    -0.65
     reporting
    -0.65
     Orwell
    -0.63
     unprotected
    -0.62
     Dispatch
    -0.61
     Titus
    -0.61
     succeeding
    -0.60
     dividing
    -0.60
     resembling
    -0.59
    POSITIVE LOGITS
    jah
    1.36
    lder
    1.36
    hammad
    1.26
    zik
    1.26
    ñ
    1.18
    htar
    1.13
    ahah
    1.10
    clair
    1.06
    ham
    1.05
    ld
    1.04
    Activations Density 0.016%

    No Known Activations