© 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. 10-RES-JB
    11. 3303
    Prev
    Next
    INDEX
    Explanations

    references to budget-related terms, particularly mentioning budget cuts or constraints

    oai_token-act-pair · gpt-3.5-turbo

    mentions of budget-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.71
    ijuana
    -0.68
    kai
    -0.67
     Jericho
    -0.67
    Magikarp
    -0.67
    uana
    -0.66
    ocrates
    -0.66
    CRIPTION
    -0.66
     Virtue
    -0.65
     Wem
    -0.64
    POSITIVE LOGITS
     deficit
    1.19
     allocations
    1.11
     shortfall
    1.06
     deficits
    1.06
     surplus
    0.97
     cuts
    0.97
     allocation
    0.94
    ing
    0.94
    ed
    0.93
     allocated
    0.87
    Activations Density 0.045%

    No Known Activations