© 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. 11-RES-JB
    11. 7607
    Prev
    Next
    INDEX
    Explanations

    controversial or negative events involving individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to incidents or actions that involve legal or criminal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.75
     eleph
    -0.66
     newcom
    -0.66
     sucker
    -0.65
     lest
    -0.61
     propri
    -0.60
     favors
    -0.58
     goalt
    -0.58
     newsp
    -0.58
     endeavor
    -0.57
    POSITIVE LOGITS
    Updated
    1.02
    Posted
    1.00
    hello
    0.91
    Britain
    0.89
    ³³³
    0.84
    Gab
    0.76
    ³³³³³³³³
    0.76
    ³³³³³³³³³³³³³³³³
    0.75
    TW
    0.75
    Bus
    0.72
    Activations Density 0.071%

    No Known Activations