© 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. 2-RES-JB
    11. 12701
    Prev
    Next
    INDEX
    Explanations

    the word "Barnes" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Barnes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.69
    ffic
    -0.65
     Finnish
    -0.64
    ixed
    -0.63
    escal
    -0.62
    pper
    -0.62
    ppy
    -0.61
    ebin
    -0.61
     Helsinki
    -0.60
    Vi
    -0.60
    POSITIVE LOGITS
     Barnes
    1.00
    aunders
    0.93
     Skydragon
    0.87
    nect
    0.83
    haw
    0.80
     Yards
    0.80
    sell
    0.79
    sey
    0.78
    emouth
    0.76
    bee
    0.76
    Activations Density 0.008%

    No Known Activations