© 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. 21809
    Prev
    Next
    INDEX
    Explanations

    discussions revolving around land use, ownership, and policy

    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
    0:0.25
    1:0.01
    2:0.22
    3:0.11
    4:0.03
    5:0.11
    6:0.05
    7:0.05
    8:0.05
    9:0.02
    10:0.03
    11:0.01
    Negative Logits
     Scream
    -2.61
     moderators
    -2.38
     SIG
    -2.32
     STD
    -2.32
     Outbreak
    -2.25
     Kappa
    -2.22
     Nemesis
    -2.21
     circadian
    -2.19
     masturb
    -2.19
     Sexy
    -2.17
    POSITIVE LOGITS
     acre
    4.53
     farmland
    4.39
     landowners
    4.25
     acres
    3.98
     leases
    3.73
    acre
    3.68
     grazing
    3.56
     holdings
    3.51
     land
    3.40
     hectares
    3.38
    Activations Density 0.206%

    No Known Activations