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. 19541
    Prev
    Next
    INDEX
    Explanations

    instances of sports-related actions and events

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts, indicating a trend or connectivity in the narrative

    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
    insula
    -0.98
    itarian
    -0.87
    payer
    -0.82
    ictionary
    -0.81
    ihu
    -0.81
    actionDate
    -0.79
    orno
    -0.78
    iste
    -0.77
    Marx
    -0.76
    uct
    -0.74
    POSITIVE LOGITS
     thus
    0.98
     then
    0.96
     teammate
    0.96
     scored
    0.94
     earns
    0.90
     Sporting
    0.90
     secondly
    0.88
     rookie
    0.85
     rookies
    0.85
     quarterbacks
    0.85
    Activations Density 0.230%

    No Known Activations