© 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. 9118
    Prev
    Next
    INDEX
    Explanations

    political terms and keywords related to speeches and statements

    oai_token-act-pair · gpt-3.5-turbo

    formal statements and speeches made by individuals

    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
    BIP
    -0.67
    Wonder
    -0.65
    é¾įå¥ij士
    -0.64
     Generations
    -0.63
     Pryor
    -0.62
    uyomi
    -0.62
    Best
    -0.62
    Myth
    -0.62
     Jenner
    -0.61
     Weed
    -0.61
    POSITIVE LOGITS
     televised
    1.15
     emphas
    1.07
     quoted
    1.04
     authorised
    1.03
     translated
    0.99
     criticised
    0.96
     Nato
    0.94
     extracts
    0.93
     veiled
    0.92
    zbollah
    0.91
    Activations Density 0.273%

    No Known Activations