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. 2098
    Prev
    Next
    INDEX
    Explanations

    information about individuals involved in various incidents or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in various contexts, particularly in relation to incidents or events

    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
     everlasting
    -0.78
    foundation
    -0.71
     emphasizing
    -0.71
     Anything
    -0.64
     concentrating
    -0.64
     focusing
    -0.63
     excluding
    -0.61
    ³³³³
    -0.61
     refining
    -0.61
     everywhere
    -0.60
    POSITIVE LOGITS
     died
    1.08
     allegedly
    1.07
     escaped
    1.00
     perished
    0.99
     survived
    0.98
     appeared
    0.97
     fled
    0.97
     disappeared
    0.97
     crashed
    0.96
     belonged
    0.95
    Activations Density 0.135%

    No Known Activations