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. 7349
    Prev
    Next
    INDEX
    Explanations

    words related to extreme temperature conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cold and warm weather conditions and their effects

    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
     resemb
    -0.74
    iture
    -0.72
     guiIcon
    -0.70
    ICLE
    -0.69
    66666666
    -0.68
     smallest
    -0.67
    {"
    -0.64
    udeau
    -0.62
     Improvement
    -0.62
    vernment
    -0.62
    POSITIVE LOGITS
    Cold
    0.90
    weather
    0.87
    pressed
    0.87
    cold
    0.84
    blooded
    0.84
     humid
    0.82
    sensitive
    0.81
    climate
    0.77
    stress
    0.77
    oxide
    0.74
    Activations Density 0.129%

    No Known Activations