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. 23523
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Mark."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mark"

    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
    committee
    -0.92
    cffff
    -0.81
    milo
    -0.81
    ibaba
    -0.76
    pmwiki
    -0.76
     decomp
    -0.75
    culus
    -0.73
    urses
    -0.71
    bably
    -0.70
    dayName
    -0.69
    POSITIVE LOGITS
     Twain
    1.16
     Mark
    1.07
    Mark
    1.00
    emark
    0.93
    mark
    0.90
    marks
    0.88
     Zuckerberg
    0.84
     Marks
    0.83
     Thom
    0.80
     Gat
    0.77
    Activations Density 0.014%

    No Known Activations