© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 4902
    Prev
    Next
    INDEX
    Explanations

    ingredients in recipes related to tomatoes

    oai_token-act-pair · gpt-3.5-turbo

    references to tomatoes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -1.07
    rams
    -1.00
    ingham
    -0.93
    lass
    -0.85
    mare
    -0.77
    mable
    -0.77
    taking
    -0.77
    olulu
    -0.76
    dit
    -0.76
    ationally
    -0.76
    POSITIVE LOGITS
     tomatoes
    1.05
     tomato
    0.83
     juice
    0.83
    fruit
    0.81
    ographical
    0.77
    ISO
    0.74
     plants
    0.74
     basil
    0.73
     vegetables
    0.70
     paste
    0.70
    Activations Density 0.078%

    No Known Activations