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. 15457
    Prev
    Next
    INDEX
    Explanations

    keywords related to cooling systems and temperature regulation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cool" in various contexts

    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
    lessly
    -0.64
     Canaver
    -0.63
    Reloaded
    -0.63
     Ethics
    -0.61
    PLE
    -0.61
     Pengu
    -0.61
     Dele
    -0.61
    riage
    -0.61
     Hodg
    -0.60
    ©¶æ
    -0.60
    POSITIVE LOGITS
    idge
    1.08
    oola
    0.94
    ness
    0.93
    achine
    0.88
    est
    0.81
     breeze
    0.80
    pants
    0.79
    hens
    0.78
    spot
    0.78
    estone
    0.77
    Activations Density 0.033%

    No Known Activations