© 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. 10-RES-JB
    11. 16643
    Prev
    Next
    INDEX
    Explanations

    phrases related to temperature and maintaining appropriate conditions

    oai_token-act-pair · gpt-3.5-turbo

    comparisons and discussions related to temperature conditions

    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
    phabet
    -0.96
    farious
    -0.87
     Dupl
    -0.83
    Transaction
    -0.80
    Tro
    -0.79
    JV
    -0.79
     Transaction
    -0.78
     0004
    -0.77
     Uri
    -0.75
    azon
    -0.75
    POSITIVE LOGITS
     temperatures
    2.00
     temperature
    1.95
     humidity
    1.91
     cooling
    1.84
    Temperature
    1.82
     colder
    1.79
     heating
    1.77
     warmer
    1.70
     heater
    1.68
     heat
    1.66
    Activations Density 0.638%

    No Known Activations