© 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 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. 22126
    Prev
    Next
    INDEX
    Explanations

    references to prefixes or suffixes in the context of words and phrases

    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
    0:0.24
    1:0.04
    2:0.12
    3:0.14
    4:0.05
    5:0.10
    6:0.04
    7:0.06
    8:0.05
    9:0.05
    10:0.04
    11:0.02
    Negative Logits
     Daly
    -2.54
     Vulkan
    -2.50
     Radeon
    -2.45
     Avalon
    -2.33
     Dav
    -2.22
     Jericho
    -2.20
     Stef
    -2.18
     Volunte
    -2.14
    AMD
    -2.11
     Dw
    -2.09
    POSITIVE LOGITS
     syll
    4.10
     noun
    3.95
     pronouns
    3.92
     spelling
    3.89
     conson
    3.84
     verbs
    3.82
     vowel
    3.81
     grammar
    3.80
     pronoun
    3.80
     phrases
    3.68
    Activations Density 0.507%

    No Known Activations