© 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. 4934
    Prev
    Next
    INDEX
    Explanations

    repetitive occurrences of the string "ub" followed by a high activation value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ub."

    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
    ensis
    -0.67
     Lan
    -0.64
     onto
    -0.61
     arrivals
    -0.59
     Victims
    -0.59
     incomes
    -0.58
    EMENT
    -0.58
     Crimes
    -0.58
     Leaving
    -0.58
     assists
    -0.57
    POSITIVE LOGITS
    ub
    4.35
    ubs
    2.78
    UB
    2.15
    ubi
    2.04
    ubes
    1.94
    ube
    1.85
    uble
    1.77
    ubb
    1.77
    uber
    1.70
    uba
    1.57
    Activations Density 0.013%

    No Known Activations