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. 6-RES-JB
    6. 3841
    Prev
    Next
    INDEX
    Explanations

    news headlines with mentions of "RIA Novosti," a Russian state-owned news agency

    oai_token-act-pair · gpt-3.5-turbo

    references to the Russian news agency "RIA Novosti."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iesta
    -0.70
    resses
    -0.69
    udging
    -0.65
     ants
    -0.64
    inki
    -0.64
    erella
    -0.64
    retty
    -0.63
    iful
    -0.61
     Mermaid
    -0.61
     corpus
    -0.61
    POSITIVE LOGITS
    sky
    0.73
    grad
    0.70
    士
    0.67
    vich
    0.67
    foundland
    0.65
    ivari
    0.65
     Yanuk
    0.64
    phrine
    0.64
    Ö¼
    0.64
    imester
    0.64
    Activations Density 0.121%

    No Known Activations