© 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 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. 8-RES-JB
    11. 11171
    Prev
    Next
    INDEX
    Explanations

    mentions of multiple instances or occurrences of items in a context related to technology or organization

    oai_token-act-pair · gpt-3.5-turbo

    references to scalability and multiple entities in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gratitude
    -0.66
     Relief
    -0.63
    ãĤ´ãĥ³
    -0.63
    escription
    -0.63
     Freeman
    -0.62
    nce
    -0.62
    PDATE
    -0.60
     Cloak
    -0.60
     Emerson
    -0.59
    arton
    -0.59
    POSITIVE LOGITS
     simultaneously
    1.46
     consecut
    1.35
     concurrently
    1.20
     apiece
    1.15
     together
    1.09
     alike
    1.09
     interconnected
    1.04
     simultaneous
    1.01
     vying
    1.00
     individually
    0.98
    Activations Density 0.504%

    No Known Activations