© 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. 11-RES-JB
    11. 20524
    Prev
    Next
    INDEX
    Explanations

    phrases related to wrapping or covering something

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of wrapping and containment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anan
    -0.75
    sonian
    -0.72
    antine
    -0.70
     recomm
    -0.70
    orie
    -0.68
    é¾įå
    -0.68
    tics
    -0.66
    rade
    -0.64
    onet
    -0.64
    avanaugh
    -0.64
    POSITIVE LOGITS
     around
    1.08
     tightly
    0.96
    around
    0.93
     wrap
    0.92
     wrapped
    0.91
    wrap
    0.90
     wraps
    0.87
     shroud
    0.87
     wrapping
    0.86
     up
    0.85
    Activations Density 0.068%

    No Known Activations