© 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. 11125
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and references to physical documentation or evidence

    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
    1:0.03
    2:0.03
    3:0.10
    4:0.02
    5:0.04
    6:0.01
    7:0.05
    8:0.02
    9:0.01
    10:0.60
    11:0.02
    Negative Logits
     Lastly
    -2.23
    UTC
    -2.07
    ciating
    -1.87
    %.
    -1.87
    !".
    -1.87
     Quote
    -1.81
    thinkable
    -1.81
    venth
    -1.73
    ibia
    -1.70
    everything
    -1.70
    POSITIVE LOGITS
     or
    4.63
     Or
    3.81
    Or
    3.76
    Either
    3.52
     Either
    3.29
     either
    3.27
     OR
    3.13
    or
    3.05
    either
    2.62
     nor
    2.54
    Activations Density 0.379%

    No Known Activations