© 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. 3-RES-JB
    11. 3657
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific retail store - Walmart

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company "Wal-Mart."

    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
    ibilities
    -0.79
    lihood
    -0.78
     deaf
    -0.77
    ï¸ı
    -0.74
    icter
    -0.72
     eminent
    -0.72
    æŃ
    -0.70
    IBLE
    -0.70
    umbnail
    -0.69
     impe
    -0.69
    POSITIVE LOGITS
     Stores
    1.55
     stores
    1.01
    Mart
    0.88
    inez
    0.87
     store
    0.86
     Store
    0.85
    tsy
    0.85
     Warehouse
    0.82
    eers
    0.82
    ards
    0.81
    Activations Density 0.009%

    No Known Activations