© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    words related to negative impacts of policies or actions on various groups, such as families, workers, or the economy

    oai_token-act-pair · gpt-3.5-turbo
    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
    wcsstore
    -0.85
    canon
    -0.83
    DragonMagazine
    -0.83
    RFC
    -0.76
     Incident
    -0.72
    ulkan
    -0.72
    agram
    -0.71
    GMT
    -0.70
     chromosome
    -0.68
     confir
    -0.68
    POSITIVE LOGITS
     taxpayers
    1.37
     needy
    1.28
     families
    1.27
     disadvantaged
    1.24
     millionaires
    1.17
     businesses
    1.16
     borrowers
    1.16
     homeowners
    1.15
     corporations
    1.14
     retirees
    1.14
    Activations Density 0.379%

    No Known Activations