© 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. 0-RES-JB
    11. 12541
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Yoko" in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities with the name "oko."

    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
     CIS
    -0.67
     DHS
    -0.66
     §
    -0.66
     Hastings
    -0.66
     Stanton
    -0.65
     domain
    -0.65
     HT
    -0.62
     §§
    -0.62
     HD
    -0.62
     breed
    -0.61
    POSITIVE LOGITS
    oko
    4.42
    osuke
    1.43
    oka
    1.40
    oki
    1.40
    iko
    1.34
    ako
    1.29
    inka
    1.25
    ok
    1.17
    aku
    1.16
    oku
    1.15
    Activations Density 0.016%

    No Known Activations