© 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. 11-RES-JB
    11. 14587
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various titles such as books, movies, and music albums

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and references related to games, fiction, and mythology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sheet
    -0.84
     acceptable
    -0.74
     customary
    -0.73
    effective
    -0.72
    same
    -0.71
    uphem
    -0.71
    accessible
    -0.70
    orders
    -0.69
    handle
    -0.69
    perature
    -0.69
    POSITIVE LOGITS
     Studios
    1.25
     Technologies
    1.19
     Records
    1.16
     Entertainment
    1.15
     Films
    1.14
     Pictures
    1.10
     Rising
    1.10
     Labs
    1.09
     Books
    1.09
     Centauri
    1.09
    Activations Density 0.411%

    No Known Activations