© 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. 15766
    Prev
    Next
    INDEX
    Explanations

    expressions of authority or commands in a conversation

    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
    0:0.05
    1:0.04
    2:0.11
    3:0.19
    4:0.07
    5:0.12
    6:0.02
    7:0.14
    8:0.04
    9:0.02
    10:0.11
    11:0.04
    Negative Logits
     strikingly
    -2.25
    eatures
    -2.20
     innovations
    -2.19
     contemporaries
    -2.15
    ��
    -2.15
    ��
    -2.13
     constituents
    -2.13
     exhibited
    -2.12
     widespread
    -2.11
     experiencing
    -2.08
    POSITIVE LOGITS
     gonna
    3.04
     gotta
    2.89
     yours
    2.89
     ya
    2.81
     fuckin
    2.70
     fucking
    2.64
     fuck
    2.58
     okay
    2.45
     wanna
    2.43
     please
    2.43
    Activations Density 0.540%

    No Known Activations