© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 11537
    Prev
    Next
    INDEX
    Explanations

    references to surfaces and their interactions

    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
    1:0.05
    2:0.05
    3:0.05
    4:0.05
    5:0.04
    6:0.27
    7:0.05
    8:0.04
    9:0.22
    10:0.03
    11:0.02
    Negative Logits
    kk
    -3.57
     Ll
    -3.56
     Kak
    -3.45
     Cooper
    -3.42
     Alv
    -3.33
     Harmony
    -3.26
     Levi
    -3.25
     Dek
    -3.24
     Lilly
    -3.21
     Moff
    -3.19
    POSITIVE LOGITS
    surface
    6.89
     Surface
    6.68
     surface
    6.08
     surfaces
    5.68
    Sur
    3.83
     SUR
    3.82
     resur
    3.71
     Petersen
    3.54
     SEM
    3.51
    ousse
    3.46
    Activations Density 0.001%

    No Known Activations