© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 15915
    Prev
    Next
    INDEX
    Explanations

    names related to entertainment or famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Norton and Ortiz

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kell
    -0.79
    tered
    -0.75
    ional
    -0.75
    ebook
    -0.73
    ¤
    -0.72
    ulatory
    -0.70
    ters
    -0.70
    ulating
    -0.69
    soDeliveryDate
    -0.69
    âĸ¬âĸ¬
    -0.68
    POSITIVE LOGITS
     Norton
    1.26
    cliffe
    0.79
     Howe
    0.75
    shire
    0.73
    Downloadha
    0.70
    sson
    0.70
     Vanderbilt
    0.68
    antage
    0.68
     mosqu
    0.68
    INGTON
    0.68
    Activations Density 0.015%

    No Known Activations