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. 1-RES-JB
    6. 4524
    Prev
    Next
    INDEX
    Explanations

    names associated with the surname "Dunn."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dunn."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ľ
    -0.68
    ccording
    -0.67
     Egyptians
    -0.67
    disabled
    -0.64
     wheelchair
    -0.62
     Iran
    -0.59
    ī
    -0.58
     Tehran
    -0.57
    control
    -0.57
     Kerala
    -0.57
    POSITIVE LOGITS
     Dunn
    1.21
    igan
    1.08
    qv
    0.87
    iband
    0.87
    itor
    0.86
    ett
    0.85
    ividual
    0.84
    itto
    0.83
    ifer
    0.81
    sey
    0.81
    Activations Density 0.009%

    No Known Activations