© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7106
    Prev
    Next
    INDEX
    Explanations

    references to a specific media organization, CBC (Canadian Broadcasting Corporation)

    oai_token-act-pair · gpt-3.5-turbo
    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
    wagen
    -0.84
    ¯
    -0.72
    istration
    -0.71
    jury
    -0.70
    chest
    -0.69
    itia
    -0.67
    erva
    -0.67
    ammad
    -0.65
     caste
    -0.63
     Whedon
    -0.60
    POSITIVE LOGITS
     News
    1.17
    NEWS
    1.08
    News
    1.06
     Radio
    1.01
    Money
    0.99
     Television
    0.88
    Sports
    0.87
    news
    0.87
     Broadcasting
    0.87
     Marketplace
    0.85
    Activations Density 0.030%

    No Known Activations