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. 11-RES-JB
    6. 8674
    Prev
    Next
    INDEX
    Explanations

    trees and plants

    oai_token-act-pair · gpt-3.5-turbo

    references to trees and plants, specifically their varieties and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leaks
    -0.86
    Privacy
    -0.86
     Emails
    -0.78
    Engineers
    -0.78
    Secure
    -0.78
    ISION
    -0.77
    Interface
    -0.76
     NETWORK
    -0.76
     Survivors
    -0.76
     Imaging
    -0.76
    POSITIVE LOGITS
     oranges
    1.54
     strawberries
    1.48
     almonds
    1.44
     grapes
    1.41
     pine
    1.39
     citrus
    1.38
     mango
    1.36
     berries
    1.35
     cher
    1.32
     pineapple
    1.31
    Activations Density 0.168%

    No Known Activations