© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22503
    Prev
    Next
    INDEX
    Explanations

    words related to international environments or settings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of programming-related data types and keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mayhem
    -0.63
     places
    -0.62
     Zucker
    -0.60
     cuts
    -0.59
     Cursed
    -0.58
     leaves
    -0.57
     Fas
    -0.57
     Scotia
    -0.57
     Quote
    -0.56
     Canterbury
    -0.56
    POSITIVE LOGITS
    int
    4.14
    ints
    2.70
    INT
    2.03
    Int
    1.59
    inter
    1.41
    uint
    1.38
    bool
    1.37
     int
    1.37
    inters
    1.33
    inth
    1.33
    Activations Density 0.013%

    No Known Activations