© 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. 17565
    Prev
    Next
    INDEX
    Explanations

    concepts related to control and authority

    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
    1:0.02
    2:0.04
    3:0.19
    4:0.02
    5:0.07
    6:0.02
    7:0.05
    8:0.03
    9:0.02
    10:0.43
    11:0.03
    Negative Logits
    interstitial
    -2.05
     excuses
    -2.01
    amaz
    -1.97
     celebr
    -1.91
     introductory
    -1.90
     unsuccessful
    -1.87
     indicative
    -1.84
     stumble
    -1.80
     intentional
    -1.78
     commend
    -1.78
    POSITIVE LOGITS
     levers
    2.14
    osphere
    2.08
    uria
    2.06
     affairs
    2.03
    via
    2.02
     via
    1.98
     finances
    1.98
     [+
    1.97
     through
    1.96
    /.
    1.90
    Activations Density 0.106%

    No Known Activations