© 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. 0-RES-JB
    11. 15299
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and credit

    oai_token-act-pair · gpt-3.5-turbo

    terms related to credit and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lington
    -0.81
    leans
    -0.69
    angles
    -0.68
    shr
    -0.66
    Set
    -0.66
     Osw
    -0.65
    ites
    -0.64
    sama
    -0.64
    minist
    -0.63
    tons
    -0.62
    POSITIVE LOGITS
     credit
    3.99
    credit
    2.83
     Credit
    2.70
    Credit
    2.36
     credits
    2.28
     Credits
    1.78
     debit
    1.68
     credited
    1.57
     cred
    1.56
     attribution
    1.34
    Activations Density 0.016%

    No Known Activations