© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20985
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sequence of events or actions about to take place

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "before."

    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
    urga
    -0.74
    geist
    -0.73
    æ©
    -0.73
    ologic
    -0.68
    aternity
    -0.66
    ollen
    -0.65
    Ranked
    -0.64
    ãĥ¼ãĥ
    -0.63
    ãĤ·
    -0.62
    odied
    -0.61
    POSITIVE LOGITS
     embark
    1.05
     joining
    0.99
     proceeding
    0.98
    rely
    0.97
     concluding
    0.94
     diving
    0.94
     departing
    0.93
     committing
    0.92
     dismissing
    0.90
     entering
    0.87
    Activations Density 0.034%

    No Known Activations