© 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. 2728
    Prev
    Next
    INDEX
    Explanations

    references to statistics or demographic data

    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
    1:0.06
    2:0.05
    3:0.06
    4:0.05
    5:0.05
    6:0.27
    7:0.02
    8:0.04
    9:0.21
    10:0.04
    11:0.02
    Negative Logits
     Briggs
    -4.42
     GEAR
    -4.03
     Fract
    -3.63
    Tesla
    -3.44
    Hack
    -3.44
    hack
    -3.34
     Shack
    -3.30
     Gear
    -3.21
     Ras
    -3.14
     Mason
    -3.13
    POSITIVE LOGITS
     Population
    4.96
     population
    4.90
     audience
    4.83
    Population
    4.62
    population
    4.44
     populations
    4.24
     demographic
    3.98
     audiences
    3.86
     populated
    3.60
     POP
    3.50
    Activations Density 0.002%

    No Known Activations