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. 6261
    Prev
    Next
    INDEX
    Explanations

    names related to sports teams and medical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals associated with names that start with "Giov" or "Eug" and occurrences of the term "Bengals."

    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
    lich
    -0.84
    manship
    -0.82
    DAQ
    -0.81
    tainment
    -0.80
     Deer
    -0.78
    essional
    -0.77
    lishing
    -0.77
     MBA
    -0.73
    bucks
    -0.71
    cloth
    -0.70
    POSITIVE LOGITS
     Giov
    1.04
    asca
    0.90
    hovah
    0.87
    Ïī
    0.86
    uana
    0.86
    awei
    0.84
    avorite
    0.83
    utonium
    0.79
     tremend
    0.77
    acio
    0.77
    Activations Density 0.016%

    No Known Activations