© 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 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. 21658
    Prev
    Next
    INDEX
    Explanations

    mentions of the term 'udd', appearing in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "buddy."

    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
     isolate
    -0.65
     lapse
    -0.64
     impulse
    -0.63
     Freedom
    -0.62
     vengeance
    -0.62
     propensity
    -0.60
     unfinished
    -0.57
     flaw
    -0.57
     onward
    -0.56
     deviation
    -0.56
    POSITIVE LOGITS
    udd
    1.39
    usters
    0.93
    emouth
    0.90
    odge
    0.90
    ying
    0.89
    ington
    0.86
    issance
    0.83
    undy
    0.82
    combe
    0.82
    sworth
    0.82
    Activations Density 0.006%

    No Known Activations