© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 19375
    Prev
    Next
    INDEX
    Explanations

    information related to temperature in degrees Fahrenheit and Celsius

    oai_token-act-pair · gpt-3.5-turbo

    temperature thresholds and related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Contracts
    -0.78
    folios
    -0.75
    iture
    -0.74
     acquisitions
    -0.73
     sequels
    -0.72
     redund
    -0.72
     Cosponsors
    -0.72
     Dupl
    -0.71
     purse
    -0.70
    cash
    -0.70
    POSITIVE LOGITS
    elsius
    1.28
     temperatures
    1.14
    Temperature
    1.12
    perature
    1.11
     temperature
    1.11
     Celsius
    1.07
     humidity
    1.00
     Fahrenheit
    0.99
     lows
    0.99
     altitude
    0.98
    Activations Density 0.246%

    No Known Activations