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. 6-RES-JB
    6. 9057
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of shoes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of footwear, specifically shoes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.79
    REDACTED
    -0.72
    ITIES
    -0.72
    iversal
    -0.71
    yrinth
    -0.71
    VD
    -0.71
    PsyNetMessage
    -0.70
    SHIP
    -0.70
    CLASSIFIED
    -0.69
    erest
    -0.68
    POSITIVE LOGITS
    horn
    1.15
     shoes
    1.08
     Shoes
    0.94
    pee
    0.92
    prints
    0.92
    bridge
    0.89
    toe
    0.89
     worn
    0.84
     footwear
    0.84
     shoe
    0.83
    Activations Density 0.027%

    No Known Activations