© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12592
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that are setting up a comparison or explanation with a transition indicating a shift in context

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "otherness" or alternative perspectives

    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
    yip
    -0.87
    selage
    -0.71
    '"
    -0.70
    Ru
    -0.66
     onwards
    -0.66
    atism
    -0.65
    ulner
    -0.65
    ©¶æ
    -0.64
    idation
    -0.63
    achelor
    -0.63
    POSITIVE LOGITS
     words
    1.84
    words
    1.36
     respects
    1.13
     contexts
    1.12
     Words
    1.07
    Words
    1.05
     embodiments
    1.04
     cases
    1.03
     languages
    1.02
     terminology
    1.02
    Activations Density 0.024%

    No Known Activations