© 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 EvalsExportsinterp-engineNEWAPI 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. 16291
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms related to people or entities, especially focusing on the term "Bod"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Bod" and its variations, which seem to relate to significant events or individuals associated with that term

    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
    IELD
    -0.77
    ICO
    -0.77
     Zucker
    -0.68
     Paradox
    -0.65
     silence
    -0.63
    PLIED
    -0.61
    ZI
    -0.60
    Nazi
    -0.60
    aepernick
    -0.58
    agents
    -0.58
    POSITIVE LOGITS
    ysc
    1.04
    iless
    1.02
     Bod
    0.97
    etooth
    0.92
    ily
    0.89
    acious
    0.89
    guards
    0.89
     nodd
    0.88
    achev
    0.87
    ulla
    0.87
    Activations Density 0.007%

    No Known Activations