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. 2-RES-JB
    6. 16823
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of footwear

    oai_token-act-pair · gpt-3.5-turbo

    references to shoes and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.70
    hips
    -0.69
    ities
    -0.68
    CLASSIFIED
    -0.66
    imental
    -0.65
    autical
    -0.64
    iments
    -0.64
    HCR
    -0.63
    accompanied
    -0.62
     MacArthur
    -0.60
    POSITIVE LOGITS
     shoe
    0.99
    toe
    0.91
    horn
    0.86
     heel
    0.79
     duct
    0.79
     sock
    0.78
    baum
    0.76
    loo
    0.76
    ©¶æ
    0.74
    edo
    0.72
    Activations Density 0.007%

    No Known Activations