© 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. 1151
    Prev
    Next
    INDEX
    Explanations

    calls for help or assistance

    oai_token-act-pair · gpt-3.5-turbo

    urgent calls for help or assistance in distressing situations

    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
    yrights
    -0.86
     patents
    -0.82
     Patent
    -0.80
    bryce
    -0.79
     Curve
    -0.78
     Murdoch
    -0.74
    Clock
    -0.73
     patent
    -0.73
     infringing
    -0.71
    gemony
    -0.70
    POSITIVE LOGITS
     rescue
    1.56
     humanitarian
    1.47
     rescuing
    1.43
     aid
    1.43
     shelter
    1.41
     shelters
    1.39
     rescued
    1.38
     relief
    1.37
     resc
    1.36
     assistance
    1.34
    Activations Density 1.078%

    No Known Activations