© 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. 1-RES-JB
    11. 3536
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of undergoing or receiving some form of treatment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "undergo" and its variations

    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
    wi
    -0.78
    rug
    -0.76
     Gamb
    -0.67
    Kind
    -0.64
     rainy
    -0.63
     Rockefeller
    -0.61
     Clever
    -0.59
    Cole
    -0.59
     guy
    -0.58
    ****************
    -0.57
    POSITIVE LOGITS
     undergone
    1.33
     undergo
    1.25
     underwent
    1.13
     undergoing
    1.06
    metic
    0.87
    icter
    0.83
    uates
    0.82
    veyard
    0.81
    Downloadha
    0.81
     surgery
    0.80
    Activations Density 0.008%

    No Known Activations