© 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. 12564
    Prev
    Next
    INDEX
    Explanations

    terms related to specific cultural or historical groups, especially Anglo-Saxon and Indo-European

    oai_token-act-pair · gpt-3.5-turbo

    references to the Anglo-Saxon heritage and related geographical or cultural topics

    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
     externalToEVAOnly
    -0.97
    behavior
    -0.78
     ACTIONS
    -0.75
    çīĪ
    -0.72
    idential
    -0.71
    hid
    -0.71
    dh
    -0.70
    bub
    -0.69
    peer
    -0.68
    nos
    -0.65
    POSITIVE LOGITS
    Sax
    1.03
     Villa
    1.00
     Sax
    0.91
     Celt
    0.78
    ixture
    0.78
    ishing
    0.76
    cest
    0.75
    enhagen
    0.73
     Anglo
    0.73
    Û
    0.73
    Activations Density 0.034%

    No Known Activations