© 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. 3-RES-JB
    11. 13298
    Prev
    Next
    INDEX
    Explanations

    fruit-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to fruit

    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
    rupulous
    -0.65
    agonists
    -0.63
     Schwarzenegger
    -0.63
    citizens
    -0.62
     Govern
    -0.62
     Religious
    -0.62
    ilitary
    -0.62
    FINE
    -0.61
     Urban
    -0.61
     Residential
    -0.60
    POSITIVE LOGITS
    fruit
    1.38
     fruit
    1.21
     fruits
    1.14
    cake
    1.08
     juice
    1.06
    cakes
    1.01
    ruit
    0.91
    ruits
    0.91
     Fruit
    0.90
    nect
    0.84
    Activations Density 0.010%

    No Known Activations