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. 8-RES-JB
    6. 15431
    Prev
    Next
    INDEX
    Explanations

    both sports-related and news-related terms

    oai_token-act-pair · gpt-3.5-turbo

    specific media outlet names and their related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gui
    -0.66
    oru
    -0.64
     stride
    -0.63
     kidding
    -0.62
    peat
    -0.62
    hower
    -0.60
     pinch
    -0.60
     incoming
    -0.60
     succeeded
    -0.60
     practicable
    -0.59
    POSITIVE LOGITS
    ageddon
    0.73
     Franch
    0.73
     Sport
    0.72
     Solutions
    0.72
     Thrones
    0.69
     Nerd
    0.68
     Innov
    0.68
    idon
    0.67
     LLC
    0.66
     Berman
    0.65
    Activations Density 0.344%

    No Known Activations