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. 19205
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Poroshenko."

    oai_token-act-pair · gpt-3.5-turbo

    references to the individual "Poroshenko" and related names

    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
    sburgh
    -0.76
    DERR
    -0.76
    BILITIES
    -0.73
    ITED
    -0.73
    enegger
    -0.72
    ARS
    -0.70
    Attempts
    -0.69
    shapeshifter
    -0.68
    IBLE
    -0.67
    essors
    -0.67
    POSITIVE LOGITS
    oshenko
    1.38
    pora
    0.94
     Por
    0.94
    jug
    0.91
    rique
    0.90
    agraph
    0.89
    orus
    0.89
    neum
    0.88
    folios
    0.87
    agar
    0.85
    Activations Density 0.007%

    No Known Activations