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. 17423
    Prev
    Next
    INDEX
    Explanations

    names related to political figures or individuals involved in legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures, specifically Paul Manafort and Viktor Yanukovych

    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
    RD
    -0.78
    ALE
    -0.75
    Beer
    -0.71
    ľ
    -0.71
    RAL
    -0.70
    Self
    -0.69
    Score
    -0.68
    CAST
    -0.68
    enance
    -0.68
    optional
    -0.68
    POSITIVE LOGITS
    afort
    1.19
     Manafort
    1.17
    uchin
    0.89
    ascus
    0.83
    icter
    0.81
    iola
    0.81
    agements
    0.76
     Ukrain
    0.75
     indicted
    0.74
     indict
    0.74
    Activations Density 0.006%

    No Known Activations