© 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. 27360
    Prev
    Next
    INDEX
    Explanations

    instances of the word "still" 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
    0:0.02
    1:0.02
    2:0.10
    3:0.05
    4:0.06
    5:0.03
    6:0.10
    7:0.03
    8:0.05
    9:0.05
    10:0.08
    11:0.34
    Negative Logits
     determination
    -1.95
    20439
    -1.94
     ink
    -1.93
    iox
    -1.92
     hardness
    -1.89
    entanyl
    -1.88
     cartridge
    -1.84
     Desert
    -1.84
     claws
    -1.82
    NES
    -1.79
    POSITIVE LOGITS
     imperson
    2.10
    ominated
    2.10
     frequ
    2.10
     Restaur
    2.01
     Introdu
    1.94
     Airbnb
    1.89
     amenities
    1.84
     services
    1.83
    Interstitial
    1.82
     Person
    1.79
    Activations Density 0.003%

    No Known Activations