© 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. 12861
    Prev
    Next
    INDEX
    Explanations

    explicit references to political or criminal issues related to military or governmental contexts

    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
    0:0.04
    1:0.02
    2:0.03
    3:0.06
    4:0.03
    5:0.04
    6:0.11
    7:0.02
    8:0.03
    9:0.52
    10:0.02
    11:0.02
    Negative Logits
    ococ
    -3.44
     Berger
    -3.44
     Osh
    -3.31
    mus
    -3.23
     pneum
    -3.17
     Mog
    -3.11
    browser
    -3.10
     Shir
    -3.03
     Asheville
    -3.01
    Scot
    -2.98
    POSITIVE LOGITS
    D
    6.05
    DD
    6.01
    DF
    5.74
    d
    5.69
     DD
    5.64
    dt
    5.50
     Dong
    5.45
    dd
    5.44
    ds
    5.41
    DR
    5.36
    Activations Density 0.456%

    No Known Activations