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. 17602
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call for action or a breaking point

    oai_token-act-pair · gpt-3.5-turbo

    expressions of the word "enough" and its variations, indicating a demand for change or realization of limits

    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
    ousands
    -0.87
    Ń·
    -0.86
    afort
    -0.83
    eer
    -0.77
    eston
    -0.76
    uay
    -0.75
    MA
    -0.65
    eson
    -0.65
    ighth
    -0.65
    ift
    -0.64
    POSITIVE LOGITS
     times
    0.79
    !?
    0.66
     episodes
    0.64
    times
    0.62
     negativity
    0.61
    ?!
    0.60
    inventoryQuantity
    0.59
    !?"
    0.59
     affairs
    0.58
     credit
    0.57
    Activations Density 0.035%

    No Known Activations