© 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. 9-RES-JB
    11. 20703
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to "checks" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hots
    -0.86
    wcs
    -0.73
    æĺ
    -0.69
     Norn
    -0.68
    âĸ¬
    -0.63
     Argon
    -0.63
    BLE
    -0.63
    ãĥĩ
    -0.62
     solitary
    -0.61
    cipled
    -0.60
    POSITIVE LOGITS
    boxes
    1.04
    lists
    1.04
    er
    1.00
    enhagen
    1.00
    book
    0.94
    etts
    0.94
    strap
    0.94
    iard
    0.93
    box
    0.91
    list
    0.89
    Activations Density 0.038%

    No Known Activations