© 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. 3515
    Prev
    Next
    INDEX
    Explanations

    numerals and indicators of quantity

    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
    0:0.09
    1:0.03
    2:0.08
    3:0.06
    4:0.03
    5:0.04
    6:0.31
    7:0.02
    8:0.05
    9:0.19
    10:0.02
    11:0.03
    Negative Logits
     Carnage
    -3.92
     Mandela
    -3.86
     Sagan
    -3.73
     Davidson
    -3.64
     Brun
    -3.61
     Gomez
    -3.35
     Saga
    -3.31
    owa
    -3.29
    Nature
    -3.25
    Tag
    -3.23
    POSITIVE LOGITS
     floors
    9.03
     floor
    8.51
     Floor
    8.16
    floor
    7.75
     ceilings
    5.57
     ceiling
    5.55
     stairs
    5.52
     stair
    5.48
     elevator
    5.03
    stairs
    5.01
    Activations Density 0.002%

    No Known Activations