© 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. 10651
    Prev
    Next
    INDEX
    Explanations

    characters formatting changes in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating diplomatic or international relations contexts

    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
     Oaks
    -0.69
     hindsight
    -0.65
     homebrew
    -0.63
     Whale
    -0.62
     utilizing
    -0.61
     contemplating
    -0.61
    abouts
    -0.61
     Hancock
    -0.60
     obscurity
    -0.59
     concussion
    -0.59
    POSITIVE LOGITS
    Shape
    0.86
    Egypt
    0.86
    Foreign
    0.83
    AFP
    0.82
    SPONSORED
    0.81
    Scroll
    0.81
    Turkey
    0.80
    Saudi
    0.79
    Turkish
    0.78
    PHOTOS
    0.77
    Activations Density 0.259%

    No Known Activations