© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21793
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly Mark Zuckerberg

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Mark Zuckerberg

    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
    venge
    -0.68
    parts
    -0.68
     Dominion
    -0.65
     VIDE
    -0.64
    âĶĢâĶĢ
    -0.64
    CLE
    -0.64
    VALUE
    -0.63
    ³³³
    -0.62
    agents
    -0.62
    ROR
    -0.62
    POSITIVE LOGITS
     Zuckerberg
    1.42
     Tanz
    0.92
    geist
    0.84
    zai
    0.82
     Jinping
    0.81
    arro
    0.76
    phrine
    0.75
    \\\\\\\\
    0.74
    iets
    0.72
    ukong
    0.70
    Activations Density 0.003%

    No Known Activations