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. 8-RES-JB
    6. 18824
    Prev
    Next
    INDEX
    Explanations

    phrases related to obituaries or death announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to someone's death or tragic news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     testers
    -0.75
     qualifiers
    -0.74
    UGC
    -0.71
    FactoryReloaded
    -0.71
    rule
    -0.70
    adjust
    -0.69
    âĹı
    -0.69
     persuasion
    -0.68
    arag
    -0.68
     Surve
    -0.67
    POSITIVE LOGITS
     died
    1.48
     crem
    1.26
     perished
    1.25
     memorial
    1.25
     RIP
    1.18
     funeral
    1.17
     mourn
    1.15
    RIP
    1.15
     deceased
    1.13
     tragically
    1.09
    Activations Density 0.436%

    No Known Activations