© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5-ATT-KK
    11. 27298
    Prev
    Next
    INDEX
    Explanations

    mentions of economic concepts related to austerity measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.08
    3:0.06
    4:0.06
    5:0.06
    6:0.12
    7:0.12
    8:0.04
    9:0.06
    10:0.22
    11:0.07
    Negative Logits
    VERTISEMENT
    -2.13
     pronunciation
    -1.87
     pier
    -1.86
     flashbacks
    -1.84
     paraph
    -1.70
     resur
    -1.70
    ocry
    -1.68
     recollection
    -1.66
     quot
    -1.66
     Newsp
    -1.64
    POSITIVE LOGITS
    axis
    1.95
    覚醒
    1.95
    judicial
    1.86
    stretched
    1.81
     Commands
    1.81
    largest
    1.81
    NetMessage
    1.76
    doms
    1.76
    vir
    1.75
    SCP
    1.73
    Activations Density 0.000%

    No Known Activations