© 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. 15747
    Prev
    Next
    INDEX
    Explanations

    acronyms that start with "UT" followed by a single-character suffix

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "UT" and its variations

    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
     Clover
    -0.70
     Narc
    -0.66
     MacArthur
    -0.64
     Brom
    -0.62
     poppy
    -0.62
     Friendship
    -0.61
     Nim
    -0.60
     heroin
    -0.58
     cockpit
    -0.58
     Fle
    -0.58
    POSITIVE LOGITS
    UT
    4.18
    UTE
    2.34
    uts
    2.16
    UTION
    2.07
    ut
    1.99
     UT
    1.72
    utt
    1.40
    UR
    1.39
    UC
    1.37
    utes
    1.36
    Activations Density 0.007%

    No Known Activations