© 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. 3-RES-JB
    11. 3781
    Prev
    Next
    INDEX
    Explanations

    words related to specific types of fruits

    oai_token-act-pair · gpt-3.5-turbo

    references to fruits, particularly various types of melons, grapes, and strawberries

    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
     condem
    -0.79
    ativity
    -0.77
    trak
    -0.77
    hematic
    -0.77
    orne
    -0.75
    unci
    -0.73
    ahan
    -0.73
    ossal
    -0.70
    RAW
    -0.69
     Cosponsors
    -0.68
    POSITIVE LOGITS
    fruit
    1.58
     juice
    1.22
     fruit
    1.19
     strawberries
    1.16
     tomatoes
    1.08
     fruits
    1.07
     strawberry
    1.05
     tomato
    1.02
     avocado
    1.01
     berries
    1.01
    Activations Density 0.013%

    No Known Activations