© 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. 10-RES-JB
    11. 13886
    Prev
    Next
    INDEX
    Explanations

    mentions of social programs targeting local contractors for work opportunities

    oai_token-act-pair · gpt-3.5-turbo

    references to health and inequality issues affecting individuals and communities

    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
    ADVERTISEMENT
    -0.81
    LOS
    -0.81
     paycheck
    -0.80
    caliber
    -0.78
    toggle
    -0.78
    colored
    -0.76
    Defense
    -0.75
     nonexistent
    -0.74
     goddamn
    -0.73
     gotten
    -0.73
    POSITIVE LOGITS
     apologised
    1.67
     criticised
    1.62
     recognised
    1.54
     emphas
    1.52
     analysed
    1.37
     recognise
    1.34
     realised
    1.31
     realise
    1.27
     organised
    1.27
     recogn
    1.22
    Activations Density 0.495%

    No Known Activations