Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6844
    Prev
    Next
    INDEX
    Explanations

    items or actions related to checking and monitoring various things like emails, watches, computers, and smartphones

    oai_token-act-pair · gpt-3.5-turbo

    references to checking or verifying personal information and updates

    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
    rawdownloadcloneembedreportprint
    -0.73
     Learns
    -0.68
     impetus
    -0.65
    lasting
    -0.63
     spirited
    -0.62
     Finch
    -0.61
    blow
    -0.60
    argument
    -0.60
    -+
    -0.60
    bourg
    -0.58
    POSITIVE LOGITS
     boxes
    0.97
     balances
    0.93
     correctness
    0.86
     box
    0.85
     validity
    0.84
    boxes
    0.79
     inbox
    0.78
     eligibility
    0.76
    worthiness
    0.76
     suspic
    0.75
    Activations Density 0.115%

    No Known Activations