© 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. 7-RES-JB
    11. 12387
    Prev
    Next
    INDEX
    Explanations

    mention of specific countries in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to Malaysia and Australian contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McConnell
    -0.74
    isSpecialOrderable
    -0.69
    ĸļ
    -0.67
     treadmill
    -0.66
     dispensary
    -0.63
    inventoryQuantity
    -0.63
     Scha
    -0.62
     STATS
    -0.62
     Watson
    -0.62
     manure
    -0.61
    POSITIVE LOGITS
    ese
    1.07
    istan
    1.05
    ians
    1.01
    ian
    1.00
    ESE
    0.95
    istani
    0.90
    astern
    0.90
    ican
    0.90
    IAN
    0.89
     annexed
    0.88
    Activations Density 0.199%

    No Known Activations