© 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. 11-RES-JB
    11. 10298
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name or entity "Ky"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ky" or variants thereof

    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
    acl
    -0.66
    ework
    -0.64
    acted
    -0.63
     ASA
    -0.61
    Score
    -0.60
    CAST
    -0.60
    ajor
    -0.59
    herty
    -0.58
    shaw
    -0.58
    hetics
    -0.57
    POSITIVE LOGITS
    nect
    1.03
    ucky
    0.86
    Ky
    0.85
    orea
    0.84
    mares
    0.82
    ous
    0.82
    rie
    0.79
    usha
    0.76
    ivan
    0.74
    amine
    0.73
    Activations Density 0.043%

    No Known Activations