© 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. 5-ATT-KK
    11. 34571
    Prev
    Next
    INDEX
    Explanations

    elements related to decision-making and political actions

    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
    0:0.01
    1:0.01
    2:0.16
    3:0.09
    4:0.14
    5:0.06
    6:0.03
    7:0.03
    8:0.08
    9:0.07
    10:0.13
    11:0.13
    Negative Logits
    adium
    -1.21
    iosyncr
    -1.16
    risome
    -1.14
    ortment
    -1.09
     condensed
    -1.09
    gregation
    -1.03
    redients
    -1.03
    iuses
    -1.02
    ouls
    -1.02
     intertwined
    -1.01
    POSITIVE LOGITS
    Instead
    1.30
     Instead
    1.20
     illegally
    1.13
     voluntarily
    1.11
     peacefully
    1.10
     abruptly
    1.08
     notify
    1.06
    DERR
    1.06
     sooner
    1.05
     indefinitely
    1.02
    Activations Density 0.150%

    No Known Activations