© 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. 8748
    Prev
    Next
    INDEX
    Explanations

    instances of modular or sequential arrangements in various 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
    0:0.07
    1:0.07
    2:0.05
    3:0.13
    4:0.09
    5:0.09
    6:0.05
    7:0.06
    8:0.03
    9:0.05
    10:0.19
    11:0.06
    Negative Logits
    natureconservancy
    -2.25
     VIDEOS
    -2.03
    CVE
    -1.84
    hillary
    -1.84
    nect
    -1.81
    ��
    -1.71
    Craig
    -1.71
    oddy
    -1.68
     MILL
    -1.61
     Correct
    -1.60
    POSITIVE LOGITS
     secondly
    2.75
     consists
    2.58
     consisting
    2.25
     revolves
    2.25
     sits
    2.22
     comprises
    2.15
     awaits
    2.13
     comes
    2.03
     replaces
    1.95
     sandwic
    1.94
    Activations Density 0.095%

    No Known Activations