© 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. 0-RES-JB
    11. 11326
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Kiwanguka"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ki" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insured
    -0.66
    aclysm
    -0.65
    SQL
    -0.65
    license
    -0.65
     underwater
    -0.64
     insurance
    -0.61
     rack
    -0.61
     ObamaCare
    -0.61
     uncovered
    -0.61
     Russ
    -0.60
    POSITIVE LOGITS
     Ki
    4.37
     ki
    2.47
     Mi
    1.48
    Mi
    1.39
     Kik
    1.28
     KB
    1.17
     Chi
    1.13
     Mb
    1.12
     Kis
    1.12
     Kes
    1.08
    Activations Density 0.017%

    No Known Activations