© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 6920
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.16
    3:0.14
    4:0.02
    5:0.03
    6:0.03
    7:0.08
    8:0.06
    9:0.17
    10:0.12
    11:0.09
    Negative Logits
    dyl
    -0.98
    theless
    -0.98
     Aster
    -0.97
     appet
    -0.95
    tick
    -0.95
     neurot
    -0.95
     riff
    -0.94
    xual
    -0.93
    natureconservancy
    -0.93
    EngineDebug
    -0.91
    POSITIVE LOGITS
    roth
    1.14
    igent
    1.06
    kamp
    1.04
    者
    1.03
    gewater
    1.02
    furt
    1.02
     Toledo
    0.98
    flush
    0.98
    redit
    0.98
    heed
    0.96
    Activations Density 0.064%

    No Known Activations