© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 27375
    Prev
    Next
    INDEX
    Explanations

    the word "where" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.15
    3:0.05
    4:0.07
    5:0.04
    6:0.06
    7:0.03
    8:0.05
    9:0.04
    10:0.19
    11:0.22
    Negative Logits
    hoff
    -1.62
     estimate
    -1.51
    ulty
    -1.42
    gram
    -1.41
    istor
    -1.35
     Angular
    -1.32
     Yards
    -1.31
     Shard
    -1.31
    =-=-
    -1.28
    meric
    -1.27
    POSITIVE LOGITS
    DonaldTrump
    1.81
     [|
    1.75
    catentry
    1.74
    ortunately
    1.66
    quickShipAvailable
    1.61
     srfAttach
    1.59
     contrace
    1.58
     stret
    1.56
    stretched
    1.56
     disadvant
    1.56
    Activations Density 0.021%

    No Known Activations