Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19706
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    words that include the substring "hee"

    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
    urgy
    -0.87
    iques
    -0.78
    VIDEO
    -0.73
    ittal
    -0.73
    ainer
    -0.73
    urgical
    -0.73
    Interstitial
    -0.70
    icles
    -0.68
    ained
    -0.67
    role
    -0.65
    POSITIVE LOGITS
    hee
    1.14
    gee
    1.10
    ffe
    0.87
     Wee
    0.87
    zee
    0.85
     Kong
    0.82
    pee
    0.82
    veland
    0.79
    ze
    0.79
    zeb
    0.77
    Activations Density 0.011%

    No Known Activations