© 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. 10-RES-JB
    11. 13913
    Prev
    Next
    INDEX
    Explanations

    mentions of various items commonly associated with a cart

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "cart" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITED
    -0.76
    bek
    -0.68
     chancellor
    -0.68
    IDENT
    -0.67
     Norn
    -0.67
     Pact
    -0.65
     Triangle
    -0.63
    lihood
    -0.63
     pact
    -0.62
    ÏĤ
    -0.58
    POSITIVE LOGITS
    ilage
    1.65
    ographer
    1.42
    esian
    1.41
    ographers
    1.31
    wright
    1.19
    wheel
    1.19
    ridges
    1.19
    ography
    1.17
    whe
    1.10
    ographic
    1.09
    Activations Density 0.016%

    No Known Activations