© 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. 8-RES-JB
    11. 6327
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their roles in financial and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ç¥ŀ
    -0.84
    terness
    -0.77
    ukemia
    -0.76
     apocalypse
    -0.75
    )!
    -0.72
     greatness
    -0.72
    ongevity
    -0.71
    buquerque
    -0.71
     applause
    -0.70
     extinction
    -0.69
    POSITIVE LOGITS
     subcontract
    1.05
     Manafort
    0.98
     allegedly
    0.96
     lia
    0.96
     leased
    0.96
     purported
    0.92
     aliases
    0.92
     informant
    0.90
     Defendants
    0.89
     Defendant
    0.89
    Activations Density 1.621%

    No Known Activations