© 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 EvalsExportsinterp-engineNEWAPI 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. 18422
    Prev
    Next
    INDEX
    Explanations

    words related to stock, such as stock market, stock music, or stock ingredients

    oai_token-act-pair · gpt-3.5-turbo

    mentions of inventory or stock levels

    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
    inx
    -0.77
     Dough
    -0.72
    BLE
    -0.72
    CVE
    -0.65
    cot
    -0.63
    verson
    -0.62
    partisan
    -0.62
    soever
    -0.61
    ··
    -0.61
    apo
    -0.61
    POSITIVE LOGITS
    holders
    0.95
    holm
    0.87
    ings
    0.86
    yards
    0.78
    holder
    0.77
    ivities
    0.76
    still
    0.73
    yk
    0.72
    ament
    0.72
    clude
    0.70
    Activations Density 0.008%

    No Known Activations