© 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. 879
    Prev
    Next
    INDEX
    Explanations

    instances of the word "down."

    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
    0:0.07
    1:0.08
    2:0.08
    3:0.07
    4:0.08
    5:0.07
    6:0.09
    7:0.08
    8:0.09
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
     Bike
    -3.33
     Rocks
    -3.08
     Compass
    -2.94
     cyclist
    -2.91
     saddle
    -2.85
     Ride
    -2.81
     Ice
    -2.80
     Kimber
    -2.76
     Pearce
    -2.75
     Diamond
    -2.73
    POSITIVE LOGITS
    press
    3.24
    ollah
    3.14
    stros
    3.00
    uania
    2.98
    ongh
    2.97
    Iraq
    2.96
    orts
    2.94
    entious
    2.93
    witz
    2.86
    liament
    2.85
    Activations Density 0.000%

    No Known Activations