© 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. 24272
    Prev
    Next
    INDEX
    Explanations

    words related to specific activities and tasks performed voluntarily and without pay

    oai_token-act-pair · gpt-3.5-turbo

    topics related to gaming and its community

    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
     Vaugh
    -0.50
     thous
    -0.43
     destro
    -0.41
     disadvant
    -0.41
    enegger
    -0.40
     helicop
    -0.40
     corrid
    -0.39
     Moroc
    -0.38
    _.
    -0.38
    emale
    -0.38
    POSITIVE LOGITS
     âĢº
    0.39
    \":
    0.37
     largeDownload
    0.37
    ciples
    0.37
    Baltimore
    0.35
    taboola
    0.34
    photos
    0.33
     partName
    0.33
    ihad
    0.33
    hya
    0.32
    Activations Density 4.361%

    No Known Activations