© 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. 22041
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology, specifically mentioning the browser "Edge" multiple times

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific software or gaming application called "Edge."

    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
    sie
    -0.77
    orescent
    -0.75
    enance
    -0.73
    sburgh
    -0.73
    wagen
    -0.72
     Adin
    -0.72
     subsidized
    -0.72
    anchester
    -0.71
    atem
    -0.71
     annexed
    -0.70
    POSITIVE LOGITS
     Catalyst
    1.06
    combe
    1.05
     Edge
    1.05
    Edge
    0.97
    HTML
    0.89
     Grid
    0.73
    llan
    0.71
    iger
    0.71
     Worlds
    0.70
    hill
    0.68
    Activations Density 0.008%

    No Known Activations