© 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 EvalsExportsinterp-engineNEWAPI 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. 23798
    Prev
    Next
    INDEX
    Explanations

    words or phrases ending in "ard" or "ards"

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "ard" and its variations in the text

    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
     Kut
    -0.74
     psy
    -0.66
     morp
    -0.58
     neoc
    -0.58
     repr
    -0.57
    pheus
    -0.56
     faux
    -0.56
     whatsoever
    -0.56
     Nun
    -0.55
     doct
    -0.54
    POSITIVE LOGITS
    ARD
    4.37
    ARDS
    3.56
    ards
    2.71
    ard
    2.44
    arding
    1.99
    arded
    1.88
    ardo
    1.58
    ELD
    1.39
    arde
    1.37
    ART
    1.33
    Activations Density 0.006%

    No Known Activations