© 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. 11-RES-JB
    11. 5213
    Prev
    Next
    INDEX
    Explanations

    phrases related to socio-economic issues, particularly focusing on disparities and policies

    oai_token-act-pair · gpt-3.5-turbo
    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
    rency
    -0.64
     Communism
    -0.63
    tackle
    -0.62
    washing
    -0.62
    fulness
    -0.62
    Appearances
    -0.61
     communism
    -0.61
    wcsstore
    -0.61
    Episode
    -0.61
     Matters
    -0.61
    POSITIVE LOGITS
     poorest
    1.42
     elderly
    1.33
     wealthiest
    1.31
     unemployed
    1.20
     youngest
    1.18
     mentally
    1.16
     uninsured
    1.15
     sexes
    1.13
     richest
    1.07
     needy
    1.07
    Activations Density 0.200%

    No Known Activations