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. 4-RES-JB
    6. 5231
    Prev
    Next
    INDEX
    Explanations

    temperature measurements in degrees Celsius and Fahrenheit

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardless
    -0.77
    ulations
    -0.75
    ulated
    -0.73
    udeb
    -0.73
    abor
    -0.72
    ortment
    -0.71
    ulative
    -0.71
    eson
    -0.71
    inous
    -0.71
    gotten
    -0.70
    POSITIVE LOGITS
    º
    1.21
    °
    1.19
    º
    0.97
     Celsius
    0.92
     Fahrenheit
    0.91
    elsius
    0.79
    âĶĢâĶĢâĶĢâĶĢ
    0.79
     °
    0.79
     Temperature
    0.77
    Temperature
    0.75
    Activations Density 0.006%

    No Known Activations