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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7836
    Prev
    Next
    INDEX
    Explanations

    phrases related to kitchen utensils and appliances, particularly dishwashers

    oai_token-act-pair · gpt-3.5-turbo

    references to dishwashers and 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 @ 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
    */(
    -0.75
     Armory
    -0.72
    raltar
    -0.68
    sson
    -0.67
    vernment
    -0.66
    Reviewer
    -0.64
     ICC
    -0.63
    uments
    -0.63
    nesota
    -0.63
     Ammunition
    -0.63
    POSITIVE LOGITS
    washer
    1.93
    ware
    1.19
    washing
    1.13
    cloth
    1.00
     dishes
    0.94
    Ingredients
    0.94
    was
    0.91
    onest
    0.91
    bags
    0.87
    enger
    0.87
    Activations Density 0.030%

    No Known Activations