© 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. 17796
    Prev
    Next
    INDEX
    Explanations

    references to code, articles, or documentation formats

    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
    0:0.08
    1:0.23
    2:0.06
    3:0.06
    4:0.05
    5:0.05
    6:0.13
    7:0.03
    8:0.02
    9:0.19
    10:0.02
    11:0.02
    Negative Logits
     Peng
    -3.82
     cub
    -3.22
    adan
    -3.01
     Cyborg
    -2.89
     Stone
    -2.84
     shin
    -2.75
    acho
    -2.73
     Fathers
    -2.69
     Moons
    -2.68
     Mang
    -2.65
    POSITIVE LOGITS
     list
    6.69
    list
    6.58
    List
    6.21
    lists
    6.20
     List
    6.14
     LIST
    6.12
     Lists
    6.05
     lists
    5.98
    LIST
    5.83
    elist
    5.55
    Activations Density 0.020%

    No Known Activations