© 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. 1146
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or processes happening

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "occurs" and its variations, especially in the context of events or conditions

    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
    staff
    -0.65
    yright
    -0.61
     Plans
    -0.57
    worth
    -0.55
    resa
    -0.54
    idelines
    -0.53
    ETS
    -0.53
     Brands
    -0.53
    Reviewed
    -0.52
    addy
    -0.52
    POSITIVE LOGITS
     spontaneously
    1.37
     naturally
    1.13
     whenever
    1.06
     when
    1.05
     randomly
    1.02
    when
    1.01
     during
    1.00
     spor
    1.00
     AFTER
    0.99
     invol
    0.93
    Activations Density 0.222%

    No Known Activations