© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 21556
    Prev
    Next
    INDEX
    Explanations

    phrases related to consent and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.02
    2:0.08
    3:0.11
    4:0.05
    5:0.18
    6:0.04
    7:0.06
    8:0.09
    9:0.03
    10:0.08
    11:0.03
    Negative Logits
    verning
    -2.53
     �
    -2.39
    ā
    -2.36
     │
    -2.33
     democratically
    -2.32
    �
    -2.32
    ────────
    -2.27
    ||
    -2.27
     ‎
    -2.24
     conserv
    -2.19
    POSITIVE LOGITS
     diarrhea
    2.37
     PTSD
    2.32
    quit
    2.28
     Kinnikuman
    2.27
     fentanyl
    2.25
     PVC
    2.23
     euth
    2.23
     CPC
    2.21
     suicidal
    2.21
     Baz
    2.17
    Activations Density 0.000%

    No Known Activations