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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 18217
    Prev
    Next
    INDEX
    Explanations

    words related to embarrassing situations or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and contexts of the word "embarrassing."

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

    No Comments

    Negative Logits
    emis
    -0.90
    ework
    -0.85
    WORK
    -0.77
    cki
    -0.76
    ello
    -0.75
    oan
    -0.74
    runner
    -0.74
    tein
    -0.74
    claimer
    -0.74
    erent
    -0.74
    POSITIVE LOGITS
     embarrassing
    1.17
     embarrassment
    1.15
     embarrass
    1.01
     humiliating
    0.94
     embarrassed
    0.81
     humili
    0.80
     dishon
    0.78
     tarn
    0.76
     humiliation
    0.75
    faced
    0.75
    Activations Density 0.008%

    No Known Activations