© 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. 2-RES-JB
    11. 23735
    Prev
    Next
    INDEX
    Explanations

    mentions of embarrassing situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "embarrassing" and its variations or synonyms

    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
    emis
    -0.90
    ivism
    -0.82
    ework
    -0.80
    oan
    -0.78
    tein
    -0.76
    sword
    -0.75
    ranch
    -0.75
    erential
    -0.74
    erd
    -0.74
    lance
    -0.73
    POSITIVE LOGITS
     embarrassing
    1.22
     embarrassment
    1.11
     embarrass
    1.02
     humiliating
    0.98
     humili
    0.86
     embarrassed
    0.83
    faced
    0.78
     srfAttach
    0.78
     humiliation
    0.76
     humiliated
    0.76
    Activations Density 0.016%

    No Known Activations