Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11799
    Prev
    Next
    INDEX
    Explanations

    mentions of kitchen utensils or appliances, particularly dishwashers

    oai_token-act-pair · gpt-3.5-turbo

    references to dishes and dishwashers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Armory
    -0.77
    nesota
    -0.68
     Gat
    -0.67
    vernment
    -0.67
     ICC
    -0.65
     Kindle
    -0.65
     Ammunition
    -0.65
     Ops
    -0.63
    Reviewer
    -0.63
     Convention
    -0.62
    POSITIVE LOGITS
    washer
    1.91
    washing
    1.08
    ware
    1.04
     dishes
    0.99
    stall
    0.92
     dish
    0.91
    Ingredients
    0.91
    cloth
    0.88
    was
    0.86
    cake
    0.85
    Activations Density 0.017%

    No Known Activations