© 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. 11-RES-JB
    11. 17474
    Prev
    Next
    INDEX
    Explanations

    events, ceremonies, and gatherings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naires
    -0.68
    eny
    -0.65
    catentry
    -0.64
    snap
    -0.64
    ying
    -0.63
    illing
    -0.63
    hak
    -0.62
    ierrez
    -0.62
    dylib
    -0.61
    isen
    -0.61
    POSITIVE LOGITS
     held
    1.49
     attended
    1.44
     hosted
    1.41
     postponed
    1.33
     convened
    1.31
     cancelled
    1.30
     streamed
    1.27
     conducted
    1.26
     canceled
    1.25
     presided
    1.24
    Activations Density 0.184%

    No Known Activations