© 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. 4-RES-JB
    11. 7009
    Prev
    Next
    INDEX
    Explanations

    websites and online resources

    oai_token-act-pair · gpt-3.5-turbo

    content related to websites and their features

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

    No Comments

    Negative Logits
     gases
    -0.70
    idious
    -0.68
     impe
    -0.66
    iev
    -0.64
    luster
    -0.63
    amount
    -0.63
     calculus
    -0.61
    ework
    -0.61
     upro
    -0.61
    peat
    -0.61
    POSITIVE LOGITS
     URL
    0.94
     www
    0.90
     "@
    0.86
     URLs
    0.86
     bulletin
    0.86
     Whats
    0.84
     publishing
    0.84
     website
    0.83
     websites
    0.81
    accessible
    0.80
    Activations Density 0.620%

    No Known Activations