© 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. 15838
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of the "heart."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated usage of the phrase "of", possibly indicating a focus on relationships or connections between elements

    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
    agy
    -0.74
     ACTIONS
    -0.72
     Flavoring
    -0.69
    562
    -0.66
    airs
    -0.66
    ooters
    -0.66
     ranks
    -0.65
    ux
    -0.65
    iets
    -0.63
     WATCHED
    -0.61
    POSITIVE LOGITS
     Christ
    0.90
     Jesus
    0.81
     Scripture
    0.77
    Beast
    0.76
     prophecy
    0.74
     Islam
    0.74
     truth
    0.73
     Almighty
    0.72
     adversity
    0.72
     Pablo
    0.72
    Activations Density 0.129%

    No Known Activations