© 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. 11627
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "the" in various contexts

    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
    geist
    -0.98
    ageddon
    -0.75
    adeon
    -0.70
    galitarian
    -0.70
    lins
    -0.69
    200000
    -0.68
    ²¾
    -0.63
    omics
    -0.63
    berries
    -0.63
     indeed
    -0.62
    POSITIVE LOGITS
     Associated
    1.14
     longest
    1.07
     largest
    1.06
     latest
    1.03
     latter
    1.02
     culmination
    1.00
     Huffington
    0.98
     spokesman
    0.94
     highest
    0.94
     equivalent
    0.91
    Activations Density 0.094%

    No Known Activations