© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 5917
    Prev
    Next
    INDEX
    Explanations

    mentions of footwear, specifically shoes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of shoes

    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
    PsyNetMessage
    -0.74
     subp
    -0.74
    76561
    -0.65
     Huntington
    -0.64
     aviation
    -0.62
    SHIP
    -0.60
    itative
    -0.60
    iminary
    -0.60
    itement
    -0.59
     Sherman
    -0.59
    POSITIVE LOGITS
     shoes
    1.21
     Shoes
    1.18
    horn
    0.97
    bridge
    0.95
     socks
    0.92
     Boots
    0.89
    prints
    0.88
     footwear
    0.87
     sneakers
    0.85
     shoe
    0.85
    Activations Density 0.012%

    No Known Activations