© 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. 19409
    Prev
    Next
    INDEX
    Explanations

    mentions of dishwashing activities or dishes in a context unrelated to food

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of dishes

    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
     Armory
    -0.75
    nesota
    -0.71
    vernment
    -0.70
     Kindle
    -0.67
    Reviewer
    -0.65
     Gat
    -0.65
     Ops
    -0.64
     Morse
    -0.61
     Arkham
    -0.60
     annex
    -0.60
    POSITIVE LOGITS
    washer
    1.87
    washing
    1.14
     dishes
    1.04
    ware
    1.04
     dish
    1.02
    Ingredients
    0.90
    cake
    0.89
    stall
    0.86
    was
    0.84
    irez
    0.82
    Activations Density 0.009%

    No Known Activations