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

    Neuronpedia

    Jacobian LensNEW
    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. 22522
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or donations

    oai_token-act-pair · gpt-3.5-turbo

    references to financial proceeds

    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
    aptic
    -0.66
    tem
    -0.64
     tire
    -0.63
    OWN
    -0.62
     sher
    -0.60
    headed
    -0.60
     Siri
    -0.60
     Yosemite
    -0.59
     Solid
    -0.59
     Mirror
    -0.59
    POSITIVE LOGITS
     proceeds
    1.35
     Proceed
    1.17
    ivism
    0.82
    externalActionCode
    0.77
     giveaways
    0.77
    oteric
    0.76
    laughter
    0.75
    fund
    0.74
    itters
    0.74
    atinum
    0.73
    Activations Density 0.007%

    No Known Activations