© 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. 7832
    Prev
    Next
    INDEX
    Explanations

    instances of past events marked by the word "when"

    oai_token-act-pair · gpt-3.5-turbo

    the word "when" 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
    ictive
    -0.80
    whatever
    -0.73
    ouble
    -0.71
    omal
    -0.69
    comments
    -0.67
    arling
    -0.64
    uce
    -0.62
    gra
    -0.62
    pmwiki
    -0.62
    gem
    -0.62
    POSITIVE LOGITS
    soever
    1.12
     he
    1.02
     they
    1.01
     confronted
    0.99
     asked
    0.95
     contacted
    0.95
     she
    0.91
     interviewed
    0.80
     approached
    0.79
     questioned
    0.76
    Activations Density 0.099%

    No Known Activations