© 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. 8-RES-JB
    11. 18664
    Prev
    Next
    INDEX
    Explanations

    informational statements or updates about various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate important information or things the reader should pay attention to

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hierarchical
    -0.70
     stabilization
    -0.69
     subordinates
    -0.68
     equilibrium
    -0.68
     retracted
    -0.63
     releasing
    -0.63
     advances
    -0.63
     conducts
    -0.63
     revers
    -0.62
     instituted
    -0.62
    POSITIVE LOGITS
     yourself
    0.83
     geek
    0.77
     yourselves
    0.76
     watching
    0.75
     indulge
    0.75
    audi
    0.74
    tainment
    0.74
     reading
    0.73
     binge
    0.73
     browsing
    0.72
    Activations Density 0.711%

    No Known Activations