© 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. 4644
    Prev
    Next
    INDEX
    Explanations

    mentions of experiences or observations that are unique, new, or previously unknown

    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
    2:0.04
    3:0.11
    4:0.02
    5:0.05
    6:0.02
    7:0.05
    8:0.01
    9:0.01
    10:0.56
    11:0.02
    Negative Logits
    Thursday
    -2.39
     tomorrow
    -2.39
    terday
    -2.38
    Wednesday
    -2.22
    Monday
    -2.15
     today
    -2.13
     Wednesday
    -2.08
     Thursday
    -2.01
    {"
    -1.98
    Tuesday
    -1.95
    POSITIVE LOGITS
     nor
    3.06
     slightest
    2.95
     EVER
    2.85
     properly
    2.77
     anywhere
    2.59
    anything
    2.56
     anything
    2.55
    ever
    2.52
     anybody
    2.46
     ever
    2.42
    Activations Density 0.243%

    No Known Activations