© 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. 2-ATT-KK
    11. 22076
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "take a look."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.02
    2:0.12
    3:0.18
    4:0.03
    5:0.09
    6:0.03
    7:0.02
    8:0.24
    9:0.06
    10:0.05
    11:0.02
    Negative Logits
     estates
    -1.60
     establishments
    -1.57
     departments
    -1.57
    ooks
    -1.46
     centres
    -1.43
     branches
    -1.40
     Fram
    -1.38
     embassies
    -1.38
     wards
    -1.35
     interfaces
    -1.35
    POSITIVE LOGITS
     standpoint
    1.54
     vibe
    1.52
     reader
    1.45
    assian
    1.38
     aback
    1.35
     perspective
    1.35
     cue
    1.33
    away
    1.31
    �
    1.31
     lesson
    1.30
    Activations Density 0.040%

    No Known Activations