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. 3-RES-JB
    6. 10407
    Prev
    Next
    INDEX
    Explanations

    references to the weight measurement "ounce"

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities of an ounce, particularly in relation to marijuana and pricing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idential
    -0.74
    ised
    -0.66
    generated
    -0.65
    iding
    -0.63
    ective
    -0.63
    western
    -0.63
    hov
    -0.62
    communications
    -0.62
    nda
    -0.61
    chy
    -0.59
    POSITIVE LOGITS
     ounce
    1.02
     oz
    0.89
    eki
    0.88
     Flask
    0.82
     ounces
    0.82
     Seym
    0.81
    MENTS
    0.79
    acity
    0.78
    cake
    0.77
    ickr
    0.73
    Activations Density 0.014%

    No Known Activations