© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 11115
    Prev
    Next
    INDEX
    Explanations

    words related to political or geographical context

    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
    1:0.01
    2:0.06
    3:0.45
    4:0.02
    5:0.09
    6:0.02
    7:0.04
    8:0.03
    9:0.01
    10:0.10
    11:0.02
    Negative Logits
     failures
    -2.01
     inspections
    -1.97
    Testing
    -1.93
     pressures
    -1.92
     resilience
    -1.90
     efforts
    -1.89
    storms
    -1.89
    workers
    -1.89
     unprepared
    -1.86
     shoppers
    -1.85
    POSITIVE LOGITS
     noun
    3.98
     slang
    3.72
     surname
    3.71
     adjective
    3.70
     name
    3.67
     abbre
    3.66
     phrase
    3.60
     suffix
    3.60
     nickname
    3.43
     descriptor
    3.40
    Activations Density 1.284%

    No Known Activations