© 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. 11-RES-JB
    11. 3539
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and lending practices

    oai_token-act-pair · gpt-3.5-turbo

    economic terms and concepts related to investment and lending practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atoon
    -0.77
    paralle
    -0.75
    Dialogue
    -0.74
     Ribbon
    -0.74
    Jess
    -0.74
    eyes
    -0.72
     ACLU
    -0.70
     Compton
    -0.69
    FTWARE
    -0.69
    ukemia
    -0.68
    POSITIVE LOGITS
     invest
    1.49
     borrow
    1.43
     deposit
    1.41
     liquidity
    1.40
     lend
    1.38
     reinvest
    1.35
     hedge
    1.33
     invests
    1.33
     repay
    1.32
     withdraw
    1.28
    Activations Density 0.248%

    No Known Activations