© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3350
    Prev
    Next
    INDEX
    Explanations

    references to studies and citations in academic writing

    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
    1:0.04
    2:0.05
    3:0.10
    4:0.30
    5:0.09
    6:0.05
    7:0.09
    8:0.05
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
    Interstitial
    -2.89
    entimes
    -2.73
    culosis
    -2.72
    incial
    -2.67
    accompan
    -2.64
     counterfeit
    -2.58
    iscal
    -2.56
     usb
    -2.54
    restling
    -2.52
    Hispanic
    -2.50
    POSITIVE LOGITS
     Atkinson
    4.08
     Keller
    3.89
     Barker
    3.85
     Kessler
    3.84
     Kuh
    3.83
     Klein
    3.80
     Ko
    3.79
     Mü
    3.73
     Coch
    3.71
     Bates
    3.71
    Activations Density 0.016%

    No Known Activations