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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 8295
    Prev
    Next
    INDEX
    Explanations

    references to 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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.69
    FU
    -0.69
     VIDE
    -0.68
    independent
    -0.63
     Rite
    -0.63
    CLE
    -0.61
    Ct
    -0.60
    wives
    -0.60
     conflicting
    -0.60
    ³³³
    -0.58
    POSITIVE LOGITS
     Zuckerberg
    1.11
    ervative
    0.84
     Tanz
    0.84
    holes
    0.82
    zai
    0.77
     Jinping
    0.76
    zee
    0.74
     Hots
    0.74
    enthal
    0.72
    ipedia
    0.71
    Activations Density 0.008%

    No Known Activations