© 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. 10-RES-JB
    11. 19080
    Prev
    Next
    INDEX
    Explanations

    terms related to economic deficits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic deficits and their variations

    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
    ĪĴ
    -0.81
    ADRA
    -0.74
    ijuana
    -0.73
    ĨĴ
    -0.72
    WAYS
    -0.71
    endez
    -0.67
     Aval
    -0.67
    osate
    -0.65
    icably
    -0.65
    arth
    -0.63
    POSITIVE LOGITS
     reduction
    1.10
     deficit
    1.00
     incurred
    0.97
     shortfall
    0.92
     Reduction
    0.90
     multiplier
    0.87
     deficits
    0.86
     reductions
    0.83
     ratio
    0.83
     spending
    0.80
    Activations Density 0.027%

    No Known Activations