© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14814
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and funding

    oai_token-act-pair · gpt-3.5-turbo

    instances where funds or financial resources are discussed or allocated for various purposes

    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
    yip
    -0.97
    soType
    -0.83
    etheless
    -0.81
    xual
    -0.73
    iquette
    -0.72
    llah
    -0.71
    ÃĽ
    -0.69
    namese
    -0.69
    notations
    -0.69
    onyms
    -0.66
    POSITIVE LOGITS
     upkeep
    1.36
     expenses
    1.29
     projects
    1.13
     coffers
    1.10
     repairs
    1.10
     salaries
    1.08
     costs
    1.06
     renovations
    1.05
     expenditures
    1.01
     renovation
    0.97
    Activations Density 0.551%

    No Known Activations