© 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. 12479
    Prev
    Next
    INDEX
    Explanations

    propper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent figures or events in technology and media

    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
    rame
    -0.84
     namely
    -0.82
    etheless
    -0.75
    ividual
    -0.73
     comprised
    -0.73
     gradually
    -0.73
    involved
    -0.73
     situated
    -0.71
    erred
    -0.70
    affected
    -0.70
    POSITIVE LOGITS
     Titanic
    1.35
     Statue
    1.28
     Oscars
    1.28
     Beatles
    1.27
     Kardash
    1.27
     pope
    1.21
     Dalai
    1.21
     Quran
    1.12
     apocalypse
    1.11
     Olympics
    1.09
    Activations Density 0.472%

    No Known Activations