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

    Neuronpedia

    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. 15814
    Prev
    Next
    INDEX
    Explanations

    references to the biological agent known as anthrax

    oai_token-act-pair · gpt-3.5-turbo

    references to anthrax, particularly in the context of bioweapons and potential threats

    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
    anooga
    -0.82
    iable
    -0.82
    ifier
    -0.78
    ifiers
    -0.77
    phabet
    -0.73
    ifying
    -0.72
    restling
    -0.71
    enez
    -0.71
    iability
    -0.70
    arious
    -0.70
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.85
    ©¶æ
    0.75
    cel
    0.70
     loft
    0.69
     Xer
    0.68
     Pilgrim
    0.67
    cale
    0.65
    XXXX
    0.64
    rax
    0.63
     Zed
    0.63
    Activations Density 0.029%

    No Known Activations