© 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 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. 6-RES-JB
    11. 14526
    Prev
    Next
    INDEX
    Explanations

    proper nouns containing the syllable "Ki"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the name "Ki."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usions
    -0.80
    iners
    -0.77
    士
    -0.73
    ifiers
    -0.72
    ication
    -0.68
     Acquisition
    -0.68
    iance
    -0.67
    ines
    -0.67
     Anthem
    -0.67
    ibilities
    -0.67
    POSITIVE LOGITS
    ãĥĹ
    0.74
    pee
    0.73
    perty
    0.73
    DIV
    0.72
    fare
    0.72
    bil
    0.72
    adelphia
    0.71
    pton
    0.70
    fish
    0.70
    zeb
    0.69
    Activations Density 0.049%

    No Known Activations