Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 22862
    Prev
    Next
    INDEX
    Explanations

    mentions of sports, athletes, and competition

    oai_token-act-pair · gpt-3.5-turbo

    references to competitions or events involving participants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FBI
    -0.79
    estate
    -0.74
     FOIA
    -0.74
    inventory
    -0.72
    entimes
    -0.71
    pmwiki
    -0.70
    urches
    -0.69
    ureau
    -0.68
    Consumer
    -0.68
    SPONSORED
    -0.68
    POSITIVE LOGITS
     teammate
    1.24
     midfielder
    1.21
     Frenchman
    1.21
     goalkeeper
    1.21
     Brazilian
    1.16
     unbeaten
    1.15
     favourites
    1.14
     striker
    1.12
     Bundesliga
    1.12
     Jagu
    1.12
    Activations Density 0.418%

    No Known Activations