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. 3-RES-JB
    6. 11830
    Prev
    Next
    INDEX
    Explanations

    food preparation steps

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to meal preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     box
    -0.74
     pupp
    -0.67
     Katz
    -0.67
     penny
    -0.65
     boxes
    -0.64
     sockets
    -0.64
     conce
    -0.63
     socket
    -0.63
     masks
    -0.62
     exchanges
    -0.61
    POSITIVE LOGITS
    itude
    0.91
    aring
    0.83
    ared
    0.81
    Prep
    0.79
    arer
    0.74
    ricanes
    0.73
    iffe
    0.72
    acus
    0.72
    aq
    0.72
    Run
    0.72
    Activations Density 0.008%

    No Known Activations