© 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. 1-RES-JB
    11. 7102
    Prev
    Next
    INDEX
    Explanations

    words related to fast-paced or intense action

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of "naming" or "designating."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FAA
    -0.76
     Wikimedia
    -0.69
     Debor
    -0.67
     Britann
    -0.66
    edited
    -0.65
    displayText
    -0.63
    ellig
    -0.62
     Leilan
    -0.62
    TPP
    -0.61
    Autom
    -0.60
    POSITIVE LOGITS
    ning
    1.46
    pless
    0.91
    nings
    0.87
    bing
    0.86
    uez
    0.86
    ned
    0.83
    theless
    0.82
    NING
    0.82
    alties
    0.81
    sburg
    0.79
    Activations Density 0.006%

    No Known Activations