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

    Neuronpedia

    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. 2542
    Prev
    Next
    INDEX
    Explanations

    references to media entities and associated visual content

    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
    1:0.53
    2:0.03
    3:0.04
    4:0.03
    5:0.05
    6:0.04
    7:0.03
    8:0.02
    9:0.05
    10:0.03
    11:0.06
    Negative Logits
     Clever
    -2.83
     LU
    -2.70
     Gott
    -2.63
     1947
    -2.54
     Shank
    -2.48
     forthcoming
    -2.47
     Jub
    -2.45
    recent
    -2.43
    ano
    -2.37
     discipline
    -2.37
    POSITIVE LOGITS
     9
    4.80
    9
    4.65
     8
    3.70
    8
    3.58
    10
    3.54
    909
    3.46
    949
    3.39
    ustomed
    3.34
     10
    3.32
     ninth
    3.29
    Activations Density 0.043%

    No Known Activations