Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 16967
    Prev
    Next
    INDEX
    Explanations

    names of a specific person, "Stern", and possibly related contexts or information about them

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the surname "Stern."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vulner
    -0.72
    hift
    -0.71
    mble
    -0.68
    ournal
    -0.64
    intosh
    -0.64
    inion
    -0.64
    ³³³³³³³³³³³³³³³³
    -0.63
    teen
    -0.63
    manship
    -0.63
    ________________________________
    -0.62
    POSITIVE LOGITS
    ocrats
    0.84
    erers
    0.82
    arily
    0.79
    baugh
    0.77
    angler
    0.74
    odon
    0.74
    sburgh
    0.73
    uctions
    0.73
    ication
    0.72
    riter
    0.70
    Activations Density 0.071%

    No Known Activations