© 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. 448
    Prev
    Next
    INDEX
    Explanations

    phrases related to incidents of humanitarian crises, including violence and displacement

    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
    0:0.05
    1:0.02
    2:0.05
    3:0.12
    4:0.10
    5:0.15
    6:0.03
    7:0.06
    8:0.11
    9:0.02
    10:0.05
    11:0.18
    Negative Logits
    Ohio
    -2.86
    Sher
    -2.63
    andals
    -2.29
    ################################
    -2.29
    �
    -2.24
    Houston
    -2.22
    ―
    -2.19
    HCR
    -2.17
    adoes
    -2.14
    Roy
    -2.11
    POSITIVE LOGITS
     concess
    2.79
    llular
    2.56
     vitro
    2.43
    ixture
    2.40
    ributes
    2.26
     soluble
    2.03
    ochem
    2.02
     pH
    1.97
     placebo
    1.96
     util
    1.94
    Activations Density 0.133%

    No Known Activations