© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 9670
    Prev
    Next
    INDEX
    Explanations

    mentions of the top 1% of income earners or households in discussions related to tax policies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orbital
    -0.71
    recomm
    -0.70
    Recommend
    -0.70
     warr
    -0.70
     Archangel
    -0.68
    GMT
    -0.67
    STD
    -0.67
    Sensor
    -0.67
     protocols
    -0.66
    canon
    -0.66
    POSITIVE LOGITS
     earners
    1.16
     wealthiest
    0.99
     incomes
    0.94
     income
    0.92
    aucus
    0.87
    wage
    0.85
     borrower
    0.84
    ervatives
    0.84
     paycheck
    0.82
     Wealth
    0.82
    Activations Density 0.139%

    No Known Activations