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

    Neuronpedia

    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. 1-RES-JB
    11. 3515
    Prev
    Next
    INDEX
    Explanations

    phrases or acronyms related to the abbreviation "UL"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "UL" or related formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pocket
    -0.81
    hung
    -0.74
     Jarvis
    -0.69
    marks
    -0.69
    beat
    -0.68
    ãĢIJ
    -0.68
    hold
    -0.66
     MacArthur
    -0.65
     Dolphin
    -0.65
    away
    -0.64
    POSITIVE LOGITS
    UL
    1.37
    tymology
    1.03
    GBT
    1.01
    VIDIA
    0.97
    ULE
    0.96
     millenn
    0.94
     destro
    0.92
    PDATE
    0.91
    uilt
    0.89
    ITY
    0.88
    Activations Density 0.009%

    No Known Activations