© 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. 1-RES-JB
    11. 12864
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and digital wallets

    oai_token-act-pair · gpt-3.5-turbo

    references to financial systems or payment methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beacon
    -0.71
     Becky
    -0.70
    Weiss
    -0.68
     Wilmington
    -0.68
    ffen
    -0.66
    sylv
    -0.66
     Monroe
    -0.65
     Sinclair
    -0.64
    cru
    -0.63
     Destiny
    -0.63
    POSITIVE LOGITS
    umbai
    1.14
    jriwal
    1.12
     Sharma
    1.09
     Pradesh
    1.05
     Maharashtra
    1.05
     Nadu
    1.03
     Sabha
    1.01
     Uttar
    0.99
     Punjab
    0.97
     Hindu
    0.96
    Activations Density 1.279%

    No Known Activations