© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24057
    Prev
    Next
    INDEX
    Explanations

    references to tomatoes

    oai_token-act-pair · gpt-3.5-turbo

    references to tomatoes or related tomato products

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

    No Comments

    Negative Logits
    rams
    -0.88
    lasses
    -0.82
    trak
    -0.78
    mable
    -0.74
    pter
    -0.74
    llers
    -0.74
    gettable
    -0.73
    olulu
    -0.73
    draw
    -0.73
    ledged
    -0.70
    POSITIVE LOGITS
     tomatoes
    1.04
     tomato
    1.02
    fruit
    0.97
     juice
    0.91
    atoes
    0.89
    iculture
    0.88
    grass
    0.87
     Tomato
    0.86
     fruit
    0.85
     fruits
    0.83
    Activations Density 0.006%

    No Known Activations