© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 5227
    Prev
    Next
    INDEX
    Explanations

    instances of resignations and firings within an organizational 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
    0:0.09
    1:0.02
    2:0.14
    3:0.12
    4:0.04
    5:0.25
    6:0.02
    7:0.13
    8:0.05
    9:0.02
    10:0.05
    11:0.01
    Negative Logits
    enfranch
    -2.12
     martyr
    -2.08
     dictators
    -1.98
     Passage
    -1.95
     substitution
    -1.90
     vanish
    -1.89
     superpower
    -1.88
    death
    -1.88
     irreversible
    -1.88
     dying
    -1.86
    POSITIVE LOGITS
    lements
    2.17
    raphics
    2.02
    lied
    2.02
    metry
    1.97
    Content
    1.96
     Programming
    1.93
    management
    1.91
    cpp
    1.90
    ��
    1.89
     Catalyst
    1.86
    Activations Density 0.216%

    No Known Activations