© 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. 4375
    Prev
    Next
    INDEX
    Explanations

    dates or mentions of months and years

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.08
    4:0.04
    5:0.39
    6:0.03
    7:0.08
    8:0.04
    9:0.13
    10:0.03
    11:0.05
    Negative Logits
     retard
    -2.90
     mand
    -2.82
     executed
    -2.62
     erased
    -2.60
     fragment
    -2.57
     irreversible
    -2.55
     retarded
    -2.53
     forged
    -2.51
     sequence
    -2.49
     resh
    -2.47
    POSITIVE LOGITS
    vertisement
    3.50
    Accessory
    3.50
    arel
    3.38
    ーティ
    3.19
    Tea
    3.06
    IU
    3.04
    ategories
    2.99
    iencies
    2.95
    isSpecialOrderable
    2.93
    cellent
    2.92
    Activations Density 0.007%

    No Known Activations