© 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. 2-RES-JB
    11. 15903
    Prev
    Next
    INDEX
    Explanations

    terms related to the chemical element "zinc"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to zinc and individuals named Zap or Zy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĦ
    -0.79
    namese
    -0.76
    nel
    -0.73
    irlf
    -0.71
    ertation
    -0.70
     spirited
    -0.69
     adolesc
    -0.68
    cia
    -0.68
    omore
    -0.66
    VICE
    -0.65
    POSITIVE LOGITS
    zag
    1.03
     Zig
    0.96
    phrine
    0.85
    geist
    0.85
    zig
    0.83
    uner
    0.82
    hao
    0.82
    agame
    0.80
    umo
    0.80
    ebra
    0.79
    Activations Density 0.016%

    No Known Activations