© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20111
    Prev
    Next
    INDEX
    Explanations

    specific terms related to projects or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to whimsical and humorous themes, along with various social issues

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

    No Comments

    Negative Logits
    Interstitial
    -0.70
    emale
    -0.69
     vulner
    -0.62
    Lear
    -0.59
    âĢ¢âĢ¢
    -0.59
    lear
    -0.58
    farious
    -0.58
    Ire
    -0.57
     Gaw
    -0.56
    aeda
    -0.56
    POSITIVE LOGITS
     Vulkan
    0.55
     largeDownload
    0.53
    quickShipAvailable
    0.53
     Coverage
    0.52
     Steam
    0.48
     ROCK
    0.47
    CRIPTION
    0.47
     âĢº
    0.47
     astronomers
    0.47
     cannabis
    0.46
    Activations Density 0.414%

    No Known Activations