© 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. 3-RES-JB
    11. 20174
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the word "Yogurt"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific yogurts or references to yogurt-related topics

    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
    LESS
    -0.72
    velength
    -0.71
    ities
    -0.69
    ãĤ£
    -0.69
     Arabia
    -0.68
    ¶ħ
    -0.67
    aeda
    -0.67
    idency
    -0.66
    itance
    -0.65
    aceous
    -0.65
    POSITIVE LOGITS
     Yog
    0.87
     Pengu
    0.82
    rified
    0.81
    osal
    0.78
    rification
    0.77
    arro
    0.76
    mort
    0.74
    iants
    0.74
    ovich
    0.73
    ollo
    0.73
    Activations Density 0.007%

    No Known Activations