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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 21604
    Prev
    Next
    INDEX
    Explanations

    words related to varied temperatures

    oai_token-act-pair · gpt-3.5-turbo

    references to temperature measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oggle
    -0.71
    leg
    -0.69
    Lear
    -0.65
    bor
    -0.62
     Emblem
    -0.62
    ee
    -0.61
    quest
    -0.60
    herer
    -0.60
    oubt
    -0.60
    claw
    -0.59
    POSITIVE LOGITS
     temperatures
    3.69
     temperature
    2.16
     Temperature
    1.86
    Temperature
    1.78
     speeds
    1.58
     climates
    1.57
     humidity
    1.56
     Temper
    1.56
     winters
    1.39
     tem
    1.39
    Activations Density 0.022%

    No Known Activations