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. 9-RES-JB
    6. 10885
    Prev
    Next
    INDEX
    Explanations

    phrases related to grief and loss, especially regarding family and community impacts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of grief and remembrance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 9 - sadness

    No Comments

    Negative Logits
     evasion
    -0.81
    SpaceEngineers
    -0.78
     WP
    -0.74
     inspectors
    -0.74
    tarians
    -0.74
    tarian
    -0.74
    compliance
    -0.73
     automated
    -0.70
     bots
    -0.70
    pmwiki
    -0.69
    POSITIVE LOGITS
     memories
    1.52
     sorrow
    1.47
     sadness
    1.41
     remembrance
    1.37
     grieving
    1.34
     remem
    1.27
     mourning
    1.27
     Memories
    1.25
     grief
    1.24
     heartbreaking
    1.23
    Activations Density 1.869%

    No Known Activations