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. 10-RES-JB
    6. 4015
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy, compassion, and well wishes towards individuals facing a difficult situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sympathy and condolences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciation
    -0.86
    NetMessage
    -0.82
    estyle
    -0.81
    cum
    -0.77
    SPONSORED
    -0.77
    omsday
    -0.74
    uning
    -0.74
    initions
    -0.74
    gap
    -0.72
    ibe
    -0.71
    POSITIVE LOGITS
     families
    1.23
     victims
    1.04
     people
    0.97
     fans
    0.96
     family
    0.96
     entire
    0.96
     folks
    0.95
     brave
    0.95
     gentleman
    0.94
     brothers
    0.90
    Activations Density 0.341%

    No Known Activations