© 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. 3496
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing a significant conclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the "bottom line" or key conclusions in discussions

    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
    sure
    -0.86
    itation
    -0.81
    ITED
    -0.73
    kson
    -0.71
    itations
    -0.69
    ctica
    -0.69
    ement
    -0.67
    isconsin
    -0.67
     warr
    -0.66
    itt
    -0.62
    POSITIVE LOGITS
     line
    1.03
     drawer
    1.02
    less
    1.01
    feeding
    0.92
    line
    0.92
     bracket
    0.88
     shelf
    0.84
     Line
    0.82
    feed
    0.80
     feed
    0.80
    Activations Density 0.030%

    No Known Activations