© 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. 4-RES-JB
    11. 7470
    Prev
    Next
    INDEX
    Explanations

    phrases related to knowledge, observation, and awareness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating knowledge or awareness about a subject

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

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.67
     guiName
    -0.65
    cffffcc
    -0.62
    76561
    -0.62
    Must
    -0.61
    athi
    -0.60
    ixties
    -0.59
     Tracker
    -0.59
    è¦ļéĨĴ
    -0.59
    quart
    -0.59
    POSITIVE LOGITS
     hereafter
    0.93
     gladly
    0.78
     someday
    0.72
    fall
    0.71
    aughters
    0.71
     tomorrow
    0.70
    wagen
    0.70
    Ĥ¬
    0.69
     forever
    0.66
     rematch
    0.66
    Activations Density 0.387%

    No Known Activations