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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 5107
    Prev
    Next
    INDEX
    Explanations

    awards recognition such as Emmy, Grammy, Pulitzer, and Michelin

    oai_token-act-pair · gpt-3.5-turbo

    references to award nominations and winners, particularly for the Emmy and Pulitzer Prizes

    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
    xual
    -0.76
    quote
    -0.71
    wagen
    -0.69
    ickr
    -0.68
    uten
    -0.68
    creation
    -0.64
    folk
    -0.64
    berman
    -0.63
    ername
    -0.63
    edom
    -0.62
    POSITIVE LOGITS
     Emmy
    1.09
     Awards
    1.00
    AFTA
    0.92
     Award
    0.88
    ãĥ£
    0.77
     awards
    0.75
     award
    0.71
     ILCS
    0.70
     laure
    0.70
     Grammy
    0.70
    Activations Density 0.008%

    No Known Activations