© 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. 9819
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and measurements related to economics and demographics

    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
    1:0.07
    2:0.13
    3:0.06
    4:0.05
    5:0.05
    6:0.12
    7:0.04
    8:0.04
    9:0.25
    10:0.03
    11:0.04
    Negative Logits
     Cloud
    -3.94
    Cloud
    -3.57
     Wak
    -3.39
     Dusk
    -3.19
    cloud
    -3.17
    Fal
    -3.16
     cloud
    -3.13
     disapp
    -3.09
    Haw
    -3.08
    Flash
    -3.05
    POSITIVE LOGITS
     ratio
    7.20
     ratios
    7.18
     Ratio
    7.06
    Rat
    4.26
    rat
    4.15
     Rat
    3.89
     ration
    3.89
    rition
    3.54
     numer
    3.48
     proportions
    3.36
    Activations Density 0.001%

    No Known Activations