© 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 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. 9-RES-JB
    11. 20769
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial budgets, particularly budget cuts and constraints

    oai_token-act-pair · gpt-3.5-turbo

    references to budget-related topics

    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
    ijuana
    -0.73
    kai
    -0.72
    Magikarp
    -0.70
     Jericho
    -0.67
    imer
    -0.66
    ITH
    -0.65
    VILLE
    -0.65
    wood
    -0.64
    uana
    -0.64
    amber
    -0.64
    POSITIVE LOGITS
     allocations
    1.04
     deficit
    1.03
     deficits
    0.93
     surplus
    0.92
     shortfall
    0.92
     cuts
    0.88
     allocation
    0.86
     reconciliation
    0.85
    anza
    0.83
     budgets
    0.82
    Activations Density 0.062%

    No Known Activations