© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    mentions of cuts in budgets or services

    oai_token-act-pair · gpt-3.5-turbo

    references to budget cuts and their implications on healthcare services

    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
    wave
    -0.76
    atta
    -0.75
    lag
    -0.72
    perfect
    -0.69
    ifest
    -0.67
    agate
    -0.67
    rup
    -0.66
    oulos
    -0.65
    vable
    -0.65
    igmatic
    -0.64
    POSITIVE LOGITS
     Medicaid
    1.27
     discretionary
    1.18
     subsidies
    1.14
     Pell
    1.12
     programs
    1.10
     Medicare
    1.07
     pensions
    1.05
     spending
    1.01
     funding
    0.98
     budgets
    0.97
    Activations Density 0.203%

    No Known Activations