© 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. 9-ATT-KK
    11. 6976
    Prev
    Next
    INDEX
    Explanations

    phrases related to loyalty and transformation

    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
    0:0.08
    1:0.03
    2:0.09
    3:0.15
    4:0.09
    5:0.10
    6:0.02
    7:0.11
    8:0.09
    9:0.02
    10:0.10
    11:0.06
    Negative Logits
     ­
    -2.73
    ‑
    -2.38
    itage
    -2.22
    STEP
    -2.17
     rollout
    -2.11
    espie
    -2.11
     headline
    -2.04
    FG
    -2.02
    endment
    -2.00
    steen
    -1.97
    POSITIVE LOGITS
     Luffy
    3.35
     Likes
    2.93
     possesses
    2.81
     befriend
    2.70
     Frieza
    2.64
     hobbies
    2.53
     Zoro
    2.44
     Makoto
    2.43
     Appearance
    2.42
     Shinra
    2.41
    Activations Density 0.186%

    No Known Activations