© 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. 11642
    Prev
    Next
    INDEX
    Explanations

    facts or events mentioned followed by some reflection or comment

    oai_token-act-pair · gpt-3.5-turbo

    statements about personal experiences and reflections

    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
     Chavez
    -0.89
     Jefferson
    -0.89
     Kissinger
    -0.88
     Buchanan
    -0.88
     Nelson
    -0.86
     Cheney
    -0.86
     Pentagon
    -0.85
     Gingrich
    -0.84
     JFK
    -0.83
     Carlson
    -0.81
    POSITIVE LOGITS
    âĢ
    1.69
    ̶
    1.46
    «
    1.35
    âľ
    1.34
    âķ
    1.33
    ãĢ
    1.33
    âĹ
    1.32
    âĸł
    1.31
    âĹı
    1.29
    âĶ
    1.27
    Activations Density 0.859%

    No Known Activations