© 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. 3-RES-JB
    11. 23241
    Prev
    Next
    INDEX
    Explanations

    large monetary values expressed in millions or billions of dollars

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts and financial figures

    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
    dies
    -0.69
    bard
    -0.68
     Lovecraft
    -0.64
     Redemption
    -0.62
    alcohol
    -0.62
    NES
    -0.60
    apego
    -0.60
     Trials
    -0.59
    ibli
    -0.59
    ENC
    -0.59
    POSITIVE LOGITS
    aire
    1.12
    aires
    1.06
    naire
    0.85
    imet
    0.81
    dollar
    0.76
    illion
    0.74
    emouth
    0.74
    million
    0.73
    imeter
    0.73
    agascar
    0.72
    Activations Density 0.014%

    No Known Activations