© 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. 3-RES-JB
    11. 17485
    Prev
    Next
    INDEX
    Explanations

    phrases with the name "Linda" mentioned with different levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Linda."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kers
    -0.81
    ngth
    -0.75
    jri
    -0.73
    deck
    -0.71
    mare
    -0.71
    kies
    -0.69
    hire
    -0.68
    aic
    -0.68
    hon
    -0.68
    hma
    -0.67
    POSITIVE LOGITS
    irect
    0.77
    roid
    0.75
     Mae
    0.74
     Mandela
    0.73
    atta
    0.73
    uce
    0.72
     Linda
    0.71
    emon
    0.71
    inda
    0.71
    udi
    0.71
    Activations Density 0.006%

    No Known Activations