© 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. 16051
    Prev
    Next
    INDEX
    Explanations

    introductions and greetings in written communications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a community or group engagement

    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
    ilitarian
    -0.71
    rities
    -0.71
    arcity
    -0.68
    ividual
    -0.61
    urat
    -0.60
     mob
    -0.58
    oreal
    -0.58
    govtrack
    -0.57
    VERTISEMENT
    -0.56
    emo
    -0.55
    POSITIVE LOGITS
     Welcome
    1.06
    Welcome
    0.97
     welcome
    0.95
    Today
    0.93
    thank
    0.93
    Yesterday
    0.92
     Thank
    0.91
     congratulations
    0.91
    Firstly
    0.90
    thanks
    0.88
    Activations Density 0.136%

    No Known Activations