© 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 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. 9-RES-JB
    11. 2300
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or being taken

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taken" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.71
    ichick
    -0.68
    glers
    -0.67
    lich
    -0.63
    tions
    -0.60
    gian
    -0.60
    vine
    -0.56
    itte
    -0.55
     icing
    -0.55
     Trees
    -0.55
    POSITIVE LOGITS
     aback
    1.59
    aways
    1.12
     advantage
    1.06
     care
    0.97
     seriously
    0.89
     hostage
    0.88
     orally
    0.82
    oqu
    0.78
     Seriously
    0.77
     captive
    0.77
    Activations Density 0.034%

    No Known Activations