© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 878
    Prev
    Next
    INDEX
    Explanations

    phrases with special characters, numbers, and formatting inconsistencies

    oai_token-act-pair · gpt-3.5-turbo

    general advice and tips for safety and functionality

    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
     newcom
    -0.79
    aditional
    -0.78
     exha
    -0.76
     eleph
    -0.74
     citiz
    -0.70
    ennes
    -0.68
     presided
    -0.68
     coron
    -0.68
     newsp
    -0.66
     constit
    -0.65
    POSITIVE LOGITS
    Tip
    0.95
    Learn
    0.95
    Limit
    0.86
    Grab
    0.85
    Finish
    0.85
    Optional
    0.84
    Tips
    0.83
    Want
    0.82
     VIDEOS
    0.81
    Remove
    0.78
    Activations Density 0.211%

    No Known Activations