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. 11-RES-JB
    6. 10436
    Prev
    Next
    INDEX
    Explanations

    large numerical values, specifically related to money, budget, and financial figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to financial statistics and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spont
    -0.60
     whine
    -0.60
     inaction
    -0.56
     fight
    -0.55
     outing
    -0.55
     refusal
    -0.54
     heartbeat
    -0.54
    aghetti
    -0.53
     foray
    -0.53
    ogenesis
    -0.53
    POSITIVE LOGITS
    +.
    1.06
     whereas
    0.99
     compared
    0.98
    /.
    0.94
     apiece
    0.92
     (~
    0.92
     ÃĹ
    0.89
    +,
    0.86
    *.
    0.86
    .[
    0.85
    Activations Density 0.208%

    No Known Activations