© 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. 9-RES-JB
    11. 22862
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social issues like taxes, government programs, and public services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic issues and job loss

    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
    canon
    -0.88
    ocular
    -0.85
    TeX
    -0.78
    ealous
    -0.76
    Appearance
    -0.74
     onstage
    -0.73
    ensed
    -0.71
     sighting
    -0.68
    onduct
    -0.67
    interpret
    -0.67
    POSITIVE LOGITS
     trillions
    1.42
     millionaires
    1.19
     billions
    1.16
     impover
    1.07
     taxpayers
    1.07
     pensions
    1.04
     starving
    1.04
     untold
    1.02
     billionaires
    1.01
     subsidized
    1.00
    Activations Density 1.182%

    No Known Activations