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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 24013
    Prev
    Next
    INDEX
    Explanations

    phrases related to temperature and cooking

    oai_token-act-pair · gpt-3.5-turbo

    references to temperature and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.77
    azon
    -0.77
    business
    -0.76
    rahim
    -0.73
    enegger
    -0.72
    reprene
    -0.71
    bara
    -0.71
    utan
    -0.70
    legate
    -0.68
    naire
    -0.68
    POSITIVE LOGITS
     extremes
    1.22
     gradient
    1.07
     fluctuations
    1.01
     temperatures
    1.00
     Fahrenheit
    0.95
     difference
    0.94
    elsius
    0.94
    perature
    0.94
     temperature
    0.94
     Celsius
    0.92
    Activations Density 0.046%

    No Known Activations