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. 4-RES-JB
    6. 23739
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Anders"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named "Anders" or "Bjorn."

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

    No Comments

    Negative Logits
    meric
    -0.70
    ours
    -0.69
    iates
    -0.68
    ilts
    -0.67
    pty
    -0.66
    mary
    -0.65
    mph
    -0.64
    upuncture
    -0.62
    Mem
    -0.61
    stones
    -0.61
    POSITIVE LOGITS
     Andersen
    1.20
     Sven
    1.15
     Bj
    1.10
    gaard
    1.07
     Anders
    1.04
    sson
    0.94
    lund
    0.93
    borg
    0.92
    ø
    0.90
    gren
    0.89
    Activations Density 0.015%

    No Known Activations