© 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. 7-RES-JB
    11. 13883
    Prev
    Next
    INDEX
    Explanations

    references to various named sports teams

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ously
    -0.85
    ocene
    -0.72
    uits
    -0.69
    Jenn
    -0.68
    ibrary
    -0.68
    sbm
    -0.66
    tumblr
    -0.65
    isite
    -0.65
    stocks
    -0.64
    ths
    -0.64
    POSITIVE LOGITS
    mates
    1.22
    liquid
    1.08
    mate
    0.99
    Liquid
    0.96
     Solo
    0.91
     mates
    0.88
    peak
    0.88
     Rocket
    0.87
     Fortress
    0.86
    sters
    0.85
    Activations Density 0.046%

    No Known Activations