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

    Neuronpedia

    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. 2-RES-JB
    11. 23878
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements, specifically weights in ounces

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of weight, specifically in ounces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idential
    -0.69
    EEE
    -0.66
     Proced
    -0.65
    gotten
    -0.64
    western
    -0.63
     damned
    -0.63
    generated
    -0.62
     FANT
    -0.62
    neg
    -0.61
    information
    -0.60
    POSITIVE LOGITS
     ounce
    1.07
     oz
    1.02
     ounces
    0.94
     Seym
    0.88
    eki
    0.79
     bottles
    0.76
    ounces
    0.76
    MENTS
    0.74
    poons
    0.74
     Flask
    0.74
    Activations Density 0.008%

    No Known Activations