© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    statements about quality and comparisons in product descriptions

    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
    0:0.08
    1:0.04
    2:0.08
    3:0.06
    4:0.07
    5:0.05
    6:0.25
    7:0.03
    8:0.06
    9:0.15
    10:0.04
    11:0.03
    Negative Logits
     Tay
    -4.12
     Tinker
    -3.93
     Ivanka
    -3.76
     Kushner
    -3.69
    Farm
    -3.67
     Farm
    -3.64
     Land
    -3.52
     Eth
    -3.36
     sett
    -3.36
     leases
    -3.32
    POSITIVE LOGITS
    Bul
    8.47
    bul
    7.55
     Bullet
    7.05
     Bullets
    6.52
     Bul
    6.05
     bullet
    5.88
     bullets
    5.25
     bul
    5.00
     RPM
    4.62
     pul
    4.33
    Activations Density 0.002%

    No Known Activations