Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13371
    Prev
    Next
    INDEX
    Explanations

    instances where someone is pleading or begging

    oai_token-act-pair · gpt-3.5-turbo

    uses of the word "beg" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    visors
    -0.70
    ity
    -0.68
     Delete
    -0.65
     Cheong
    -0.65
    lance
    -0.62
    administ
    -0.62
     Ion
    -0.62
     Degree
    -0.61
     McMahon
    -0.60
    invoke
    -0.60
    POSITIVE LOGITS
     begging
    1.15
     begs
    0.92
     beg
    0.89
     begged
    0.89
    otten
    0.86
    FontSize
    0.86
     pardon
    0.81
    ModLoader
    0.80
    omorphic
    0.78
    asus
    0.76
    Activations Density 0.015%

    No Known Activations