© 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. 0-RES-JB
    11. 13187
    Prev
    Next
    INDEX
    Explanations

    the name "Joseph" and variations of the word "jealous"

    oai_token-act-pair · gpt-3.5-turbo

    the names of specific individuals, particularly those in positions of power or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pol
    -0.77
    itton
    -0.70
     Auschwitz
    -0.69
    lett
    -0.69
     braking
    -0.68
     ble
    -0.67
    usk
    -0.66
     Sty
    -0.65
     Spir
    -0.63
    itatively
    -0.62
    POSITIVE LOGITS
    eph
    4.06
    eus
    1.46
     Petraeus
    1.37
    ealous
    1.09
    huge
    1.07
    irc
    1.00
     Fitz
    1.00
    odiac
    1.00
    ihu
    0.97
     Mattis
    0.93
    Activations Density 0.068%

    No Known Activations