© 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. 1-RES-JB
    11. 24240
    Prev
    Next
    INDEX
    Explanations

    references to weights or quantities, particularly in ounces

    oai_token-act-pair · gpt-3.5-turbo

    references to ounces as a unit of measurement

    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
    ACTED
    -0.67
     Scandinavian
    -0.64
     istg
    -0.63
     Bethesda
    -0.61
    pled
    -0.61
     defense
    -0.60
    IDENT
    -0.60
     Patriot
    -0.60
     guiActiveUn
    -0.59
     Crimean
    -0.59
    POSITIVE LOGITS
    oz
    1.39
    illas
    1.08
    oa
    1.06
    arro
    1.04
    ombie
    1.02
    ozo
    1.02
    ymes
    0.90
    uana
    0.89
    anes
    0.89
    illa
    0.88
    Activations Density 0.005%

    No Known Activations