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. 15419
    Prev
    Next
    INDEX
    Explanations

    places, objects, or situations related to emptiness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of emptiness or lack of substance

    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
    arya
    -0.75
    king
    -0.70
    abol
    -0.67
    dar
    -0.66
    Murray
    -0.64
    DERR
    -0.62
    ron
    -0.62
    ector
    -0.61
    ches
    -0.61
    lag
    -0.61
    POSITIVE LOGITS
     hus
    0.92
     calories
    0.90
     storefront
    0.89
     stomach
    0.86
     spaces
    0.84
     shelves
    0.84
     backfield
    0.84
     bottles
    0.83
     shells
    0.81
     space
    0.80
    Activations Density 0.056%

    No Known Activations