© 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. 3-RES-JB
    11. 20834
    Prev
    Next
    INDEX
    Explanations

    phrases contrasting one thing to another, emphasizing the importance of the latter

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the idea of "not only" or "not just" to convey a broader significance or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oided
    -0.78
    insula
    -0.74
     largeDownload
    -0.74
    ixel
    -0.68
     Mushroom
    -0.66
    ĺħ
    -0.65
     manifold
    -0.65
    Vers
    -0.64
    azor
    -0.63
    glomer
    -0.62
    POSITIVE LOGITS
    ifiable
    1.27
    ifications
    1.06
     anymore
    0.92
    ones
    0.79
     kidding
    0.79
     desserts
    0.78
    ices
    0.77
     outright
    0.76
    IFIED
    0.75
     passively
    0.74
    Activations Density 0.038%

    No Known Activations