© 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. 11486
    Prev
    Next
    INDEX
    Explanations

    names beginning with "Abdul"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Abdul" or "Abdel."

    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
     tits
    -0.67
     comparable
    -0.64
     park
    -0.61
    ciating
    -0.60
    intendo
    -0.60
     wheelchair
    -0.59
     deaf
    -0.59
     foliage
    -0.58
     wallets
    -0.57
     playground
    -0.57
    POSITIVE LOGITS
    rahim
    1.47
     Rahman
    1.24
    rah
    1.14
    hak
    1.11
    afia
    1.09
    Rah
    1.03
     Raz
    0.99
     Hak
    0.99
    allah
    0.95
     Salam
    0.91
    Activations Density 0.025%

    No Known Activations