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. 19303
    Prev
    Next
    INDEX
    Explanations

    names related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Burr

    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
     Leone
    -0.76
    ////////////////
    -0.71
     Tigers
    -0.70
     Editors
    -0.67
    gaard
    -0.67
    e
    -0.67
    porting
    -0.65
    ////////////////////////////////
    -0.64
     Outlook
    -0.64
    jay
    -0.64
    POSITIVE LOGITS
     Burr
    1.18
    agus
    0.85
    ĵĺ
    0.84
    ikuman
    0.81
    aughs
    0.80
    ensical
    0.79
    halla
    0.79
    acci
    0.77
    ategory
    0.77
    iceps
    0.77
    Activations Density 0.013%

    No Known Activations