© 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. 21382
    Prev
    Next
    INDEX
    Explanations

    references to prestigious awards or accolades, particularly the Pulitzer Prize

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pulitzer Prize

    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
    lda
    -0.91
    ega
    -0.82
    agne
    -0.82
    ppo
    -0.80
    arde
    -0.78
    une
    -0.77
    cius
    -0.75
    bris
    -0.72
    alus
    -0.72
    ilde
    -0.72
    POSITIVE LOGITS
     Pulitzer
    1.16
    Journal
    0.96
    Publisher
    0.80
    vier
    0.78
    ionage
    0.76
    ispers
    0.76
     Newspaper
    0.76
     Prize
    0.75
     Winners
    0.75
     Newsp
    0.74
    Activations Density 0.023%

    No Known Activations