© 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. 0-RES-JB
    11. 7758
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ua" appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ua"

    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
     equally
    -0.72
     stocking
    -0.66
     racks
    -0.62
     Impl
    -0.60
     MAG
    -0.60
     degener
    -0.60
     chain
    -0.59
     lineup
    -0.58
     makeup
    -0.58
     playoffs
    -0.57
    POSITIVE LOGITS
    ua
    4.76
    UA
    2.28
    ui
    1.69
    uan
    1.63
    oa
    1.56
    uo
    1.56
    uum
    1.39
    lua
    1.38
    u
    1.34
    uay
    1.28
    Activations Density 0.013%

    No Known Activations