© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3460
    Prev
    Next
    INDEX
    Explanations

    words related to various types of equipment

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rill
    -0.88
    ril
    -0.87
    heit
    -0.85
    nee
    -0.79
    oner
    -0.77
    ectar
    -0.75
    uscript
    -0.74
    amus
    -0.73
    atorium
    -0.73
    erer
    -0.73
    POSITIVE LOGITS
     manufacturers
    1.09
     upgrades
    1.07
     rentals
    1.06
     manufacturer
    1.01
     rental
    0.99
     suppliers
    0.98
     vendors
    0.97
     purchases
    0.94
     malfunction
    0.93
     providers
    0.92
    Activations Density 0.123%

    No Known Activations