© 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. 0-RES-JB
    11. 13713
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to online stores

    oai_token-act-pair · gpt-3.5-turbo

    references to various app stores and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     particip
    -0.74
     CGI
    -0.73
     horn
    -0.69
     partic
    -0.67
    lights
    -0.64
     questioning
    -0.63
     moot
    -0.61
     blood
    -0.61
    jab
    -0.60
     sed
    -0.59
    POSITIVE LOGITS
     Store
    3.78
    Store
    2.80
     Stores
    2.66
     store
    2.57
    store
    2.43
     stores
    1.94
    stores
    1.70
     Shop
    1.59
    Shop
    1.32
     Storage
    1.27
    Activations Density 0.007%

    No Known Activations