© 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. 2299
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "wrap"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wrap."

    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
    alty
    -0.73
    ford
    -0.71
    ibr
    -0.68
     Younger
    -0.67
    rent
    -0.67
    Administ
    -0.67
     Lonely
    -0.65
    Quest
    -0.64
     discriminating
    -0.64
    alties
    -0.64
    POSITIVE LOGITS
     wrap
    3.81
     Wrap
    2.79
     wraps
    2.50
     wrapping
    2.42
    wrap
    2.41
     wrapped
    1.98
    wra
    1.81
     Wra
    1.63
     wra
    1.50
    Wra
    1.45
    Activations Density 0.018%

    No Known Activations