© 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. 8-RES-JB
    11. 17247
    Prev
    Next
    INDEX
    Explanations

    countries and international entities

    oai_token-act-pair · gpt-3.5-turbo

    references to various countries and their interactions in a global context

    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
    rison
    -0.65
    erity
    -0.65
    edi
    -0.62
    inventoryQuantity
    -0.60
    andre
    -0.60
    feed
    -0.60
    swer
    -0.58
     RTX
    -0.58
    uberty
    -0.58
    cknow
    -0.56
    POSITIVE LOGITS
     apiece
    1.16
     totaling
    1.12
     spanning
    0.95
     including
    0.91
     worldwide
    0.87
     ranging
    0.86
     consecut
    0.85
     rated
    0.85
     vying
    0.85
     plus
    0.83
    Activations Density 0.324%

    No Known Activations