© 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. 8-RES-JB
    11. 7191
    Prev
    Next
    INDEX
    Explanations

    names ending with "ki"

    oai_token-act-pair · gpt-3.5-turbo

    the term "ki" and its variations, suggesting a focus on mentions of an entity or character related to that term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nard
    -0.88
    icity
    -0.73
    Interstitial
    -0.72
    rique
    -0.72
    ICA
    -0.72
    icas
    -0.67
    %]
    -0.67
    icist
    -0.67
     Adin
    -0.65
    icals
    -0.64
    POSITIVE LOGITS
    pper
    1.20
    y
    1.10
    wi
    1.08
    yo
    1.08
    yah
    0.99
    ye
    0.97
    hao
    0.96
    pping
    0.96
    yu
    0.90
    yk
    0.90
    Activations Density 0.055%

    No Known Activations