© 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. 9-ATT-KK
    11. 8461
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and scrutiny of public figures

    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
    0:0.13
    1:0.22
    2:0.01
    3:0.02
    4:0.06
    5:0.13
    6:0.02
    7:0.11
    8:0.06
    9:0.00
    10:0.10
    11:0.09
    Negative Logits
     iod
    -2.37
    �醒
    -2.29
    Film
    -2.23
     includ
    -2.17
    Continue
    -2.12
    olson
    -2.12
     behav
    -2.09
    Writer
    -2.08
     estim
    -2.05
     Kirin
    -2.04
    POSITIVE LOGITS
     04
    3.51
     03
    3.25
     02
    3.16
     01
    3.01
     05
    2.98
     00
    2.85
     06
    2.84
     09
    2.52
     07
    2.45
    ggles
    2.39
    Activations Density 0.002%

    No Known Activations