© 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 EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 4557
    Prev
    Next
    INDEX
    Explanations

    words related to tomatoes

    oai_token-act-pair · gpt-3.5-turbo

    references to tomatoes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rams
    -0.93
    trak
    -0.85
    gettable
    -0.83
    draw
    -0.81
    lasses
    -0.77
    llers
    -0.75
    elong
    -0.74
    behavior
    -0.73
    mable
    -0.71
    lay
    -0.71
    POSITIVE LOGITS
     tomato
    1.22
     tomatoes
    1.18
     Tomato
    1.03
    fruit
    0.94
     fruit
    0.92
     plant
    0.89
     plants
    0.88
     fruits
    0.87
    bean
    0.87
     juice
    0.86
    Activations Density 0.010%

    No Known Activations