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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 21331
    Prev
    Next
    INDEX
    Explanations

    chemical laboratory procedures involving flasks and solutions

    oai_token-act-pair · gpt-3.5-turbo

    measurements and specifications related to laboratory equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.89
    astical
    -0.71
    ARCH
    -0.70
     Cynthia
    -0.69
    arak
    -0.69
     Dhabi
    -0.67
    xual
    -0.67
    recogn
    -0.67
    YP
    -0.67
    Shadow
    -0.67
    POSITIVE LOGITS
     flask
    1.65
     bottles
    1.60
     bottle
    1.55
     freezer
    1.46
     gallon
    1.43
     refill
    1.42
     drip
    1.38
     jars
    1.37
     nozzle
    1.37
     jar
    1.35
    Activations Density 0.425%

    No Known Activations