© 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. 21019
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    financial activities and behaviors that indicate a lack of investment or action in economic growth

    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
     artic
    -0.73
     Dialogue
    -0.72
     Discuss
    -0.72
    isson
    -0.71
     Topic
    -0.66
     Thought
    -0.66
    rika
    -0.65
    clair
    -0.65
     Experience
    -0.64
     Opinion
    -0.64
    POSITIVE LOGITS
     savings
    1.12
     bankrupt
    1.11
     payments
    1.08
     coffers
    1.07
     budgets
    1.07
     funds
    1.05
     billions
    1.04
     profits
    1.04
     funding
    1.04
     penn
    1.02
    Activations Density 0.303%

    No Known Activations