© 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. 9548
    Prev
    Next
    INDEX
    Explanations

    text related to community forums or discussions

    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
    0:0.28
    1:0.02
    2:0.09
    3:0.11
    4:0.05
    5:0.10
    6:0.04
    7:0.07
    8:0.07
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
     Nike
    -2.42
     Adidas
    -2.40
     Lauder
    -2.39
     Melania
    -2.38
     Macy
    -2.37
     ballet
    -2.35
    eele
    -2.33
    gradient
    -2.33
     subconscious
    -2.30
     Levi
    -2.30
    POSITIVE LOGITS
     Forums
    5.10
     moderators
    4.30
     moderator
    4.27
    forum
    4.24
     forum
    4.23
    topic
    4.17
    forums
    4.06
     Moder
    4.04
     forums
    4.00
     Forum
    3.97
    Activations Density 0.097%

    No Known Activations