© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12652
    Prev
    Next
    INDEX
    Explanations

    mentions of the Daily Caller and associated contact information

    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
    2:0.02
    3:0.07
    4:0.08
    5:0.07
    6:0.25
    7:0.02
    8:0.09
    9:0.21
    10:0.02
    11:0.03
    Negative Logits
    Sing
    -3.57
     Esk
    -3.35
     Hend
    -3.28
     Lov
    -3.23
     railway
    -3.21
     Stev
    -3.17
     Nico
    -3.16
     rockets
    -3.11
     Starship
    -3.08
     sweets
    -3.08
    POSITIVE LOGITS
     Caller
    6.54
     Cell
    3.98
    DragonMagazine
    3.80
    amera
    3.73
    DC
    3.71
     Dragon
    3.71
    cia
    3.66
     Bane
    3.60
    Ct
    3.56
    ��
    3.46
    Activations Density 0.000%

    No Known Activations