© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16306
    Prev
    Next
    INDEX
    Explanations

    words related to a certain ethnicity or nationality ending with 'ish'

    oai_token-act-pair · gpt-3.5-turbo

    derivatives or variations of the suffix "ish."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heric
    -0.61
     rall
    -0.60
    oples
    -0.60
     adren
    -0.60
    ļéĨĴ
    -0.58
     Reno
    -0.58
    sites
    -0.57
     vivo
    -0.57
    agonist
    -0.57
    FACE
    -0.56
    POSITIVE LOGITS
    ings
    0.93
    nesses
    0.90
    liest
    0.86
    roud
    0.86
    ness
    0.85
    ish
    0.83
    merga
    0.83
    ishly
    0.81
    wind
    0.78
    chev
    0.78
    Activations Density 0.015%

    No Known Activations