© 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. 7-RES-JB
    11. 20664
    Prev
    Next
    INDEX
    Explanations

    temperature measurements in degrees Celsius

    oai_token-act-pair · gpt-3.5-turbo

    temperature values expressed in degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.77
    ulations
    -0.77
     purse
    -0.75
     Saga
    -0.72
    eret
    -0.71
    ificial
    -0.70
    ulative
    -0.69
    ulation
    -0.68
    ciating
    -0.68
    eson
    -0.67
    POSITIVE LOGITS
    º
    1.12
    º
    1.09
    °
    1.02
     Celsius
    0.95
    elsius
    0.94
     Fahrenheit
    0.94
    ¿
    0.88
    ³
    0.86
    ¨
    0.84
     Temperature
    0.80
    Activations Density 0.015%

    No Known Activations