© 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. 0-RES-JB
    11. 2017
    Prev
    Next
    INDEX
    Explanations

    actions involving explosion or sudden release of energy

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "blew" or its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atar
    -0.72
    =\"
    -0.70
     Chrys
    -0.70
     ADA
    -0.69
    inct
    -0.69
    Dex
    -0.66
     Menu
    -0.66
     Nutrition
    -0.66
     Luc
    -0.65
     ASC
    -0.64
    POSITIVE LOGITS
     blew
    3.12
     blowing
    2.82
     blown
    2.42
     blows
    2.23
     blow
    2.15
    blow
    1.83
     Blow
    1.55
    blown
    1.39
     sucked
    1.31
     blasts
    1.28
    Activations Density 0.025%

    No Known Activations