© 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. 23473
    Prev
    Next
    INDEX
    Explanations

    terms related to emergencies and incidents, particularly declarations and classifications of such events

    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
    1:0.01
    2:0.08
    3:0.27
    4:0.02
    5:0.10
    6:0.02
    7:0.03
    8:0.03
    9:0.02
    10:0.30
    11:0.03
    Negative Logits
    eger
    -2.32
    ierrez
    -2.21
     Cosponsors
    -2.07
    uggets
    -2.04
    ograph
    -2.02
     salesman
    -2.01
    scenes
    -2.00
     coax
    -2.00
     glances
    -2.00
     interacts
    -1.92
    POSITIVE LOGITS
     caliphate
    2.62
     unconstitutional
    2.52
     cease
    2.51
     truce
    2.51
     cessation
    2.50
     ceasefire
    2.48
     unfit
    2.38
     sovereignty
    2.36
    ocide
    2.33
     moratorium
    2.32
    Activations Density 0.035%

    No Known Activations