© 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. 4-RES-JB
    11. 581
    Prev
    Next
    INDEX
    Explanations

    phrases related to "DA"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "DA" as well as variations of it

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

    No Comments

    Negative Logits
    erous
    -0.77
     Canaver
    -0.75
    enegger
    -0.74
    ï¸ı
    -0.71
    nz
    -0.70
    raltar
    -0.69
     McMaster
    -0.68
    ãĤ¹ãĥĪ
    -0.68
    packing
    -0.68
     Canadians
    -0.68
    POSITIVE LOGITS
    ILY
    1.25
    VE
    0.95
     DA
    0.89
    ven
    0.89
    OTA
    0.82
    hyde
    0.82
    IM
    0.74
    ESH
    0.73
    MI
    0.73
    WN
    0.72
    Activations Density 0.004%

    No Known Activations