© 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. 19812
    Prev
    Next
    INDEX
    Explanations

    coffee-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coffee and its various associations

    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
    etheless
    -0.75
    livion
    -0.73
    å£
    -0.69
    terday
    -0.68
    è¡
    -0.68
     reper
    -0.68
     nont
    -0.68
    ebin
    -0.67
    ocobo
    -0.66
    irted
    -0.65
    POSITIVE LOGITS
     Guys
    1.04
     Shop
    0.98
     Shirt
    0.98
     Fighters
    0.97
     Room
    0.97
     Launcher
    0.96
     Products
    0.94
    Style
    0.94
     Bowl
    0.94
     Blocks
    0.94
    Activations Density 0.148%

    No Known Activations