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. 1615
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical objects, specifically items related to gears

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of gear and equipment

    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
     CTR
    -0.88
    eas
    -0.68
     Mub
    -0.66
     Plain
    -0.63
    een
    -0.63
    ctuary
    -0.63
    eenth
    -0.62
     Hots
    -0.62
     Fuk
    -0.62
     Bie
    -0.61
    POSITIVE LOGITS
     gear
    1.24
    box
    0.96
    boxes
    0.96
    bag
    0.94
    paio
    0.87
     boots
    0.81
    gear
    0.79
     boxes
    0.78
     bags
    0.77
     worn
    0.77
    Activations Density 0.010%

    No Known Activations