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. 1-RES-JB
    6. 11751
    Prev
    Next
    INDEX
    Explanations

    phrases related to heat or cooking techniques involving boiling

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boil" and its variations related to cooking and temperature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phis
    -0.90
    ellen
    -0.78
    ournal
    -0.77
    aeus
    -0.76
    igers
    -0.75
    alez
    -0.74
    eele
    -0.72
    sure
    -0.71
    */(
    -0.70
    edy
    -0.70
    POSITIVE LOGITS
     boiling
    1.46
     boiled
    1.32
     boil
    1.15
     simmer
    1.09
     kettle
    1.06
     boils
    1.04
     nood
    0.85
     vinegar
    0.84
     baths
    0.83
     stove
    0.82
    Activations Density 0.009%

    No Known Activations