© 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. 20229
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to rankings and comparative analysis

    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
    0:0.05
    1:0.26
    2:0.08
    3:0.08
    4:0.07
    5:0.07
    6:0.09
    7:0.06
    8:0.02
    9:0.09
    10:0.05
    11:0.02
    Negative Logits
     Dickinson
    -2.59
     suffice
    -2.50
    GGGG
    -2.39
    fg
    -2.33
     Cutter
    -2.31
     Fixed
    -2.25
    hew
    -2.23
     Versus
    -2.22
     Draft
    -2.18
     CRC
    -2.16
    POSITIVE LOGITS
     highest
    5.41
    highest
    5.36
     lowest
    4.92
     tallest
    4.62
     smallest
    4.50
     longest
    4.39
     greatest
    4.35
    liest
    4.33
     heaviest
    4.31
    Hig
    4.14
    Activations Density 0.019%

    No Known Activations