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. 1-RES-JB
    6. 16481
    Prev
    Next
    INDEX
    Explanations

    mentions of prestigious awards, specifically the Nobel Prize

    oai_token-act-pair · gpt-3.5-turbo

    references to prestigious awards, particularly the Nobel Prize and 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
    den
    -0.82
    rir
    -0.72
    icago
    -0.66
    alter
    -0.65
    strong
    -0.65
    nes
    -0.63
    aturdays
    -0.63
    icas
    -0.61
    ocal
    -0.61
    pher
    -0.61
    POSITIVE LOGITS
     Prize
    1.42
     laureate
    1.35
     prize
    1.07
     Winners
    1.06
     Winner
    1.05
     prizes
    0.99
     awarded
    0.95
     award
    0.92
    Winner
    0.92
     winner
    0.90
    Activations Density 0.007%

    No Known Activations