© 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. 3-RES-JB
    11. 9626
    Prev
    Next
    INDEX
    Explanations

    instances where someone or something takes advantage of a situation or opportunity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "take advantage."

    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
     pronounced
    -0.70
     Alone
    -0.69
    instein
    -0.66
     unbel
    -0.64
     illum
    -0.63
    embed
    -0.62
     Matter
    -0.60
    ijk
    -0.60
     obliged
    -0.60
     Regarding
    -0.59
    POSITIVE LOGITS
     shortcuts
    0.88
    uristic
    0.82
    umbnails
    0.77
    eering
    0.73
    prising
    0.73
     tricks
    0.72
    glers
    0.72
    ãĥį
    0.70
    rand
    0.70
    æ©
    0.69
    Activations Density 0.107%

    No Known Activations