© 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. 3-ATT-KK
    11. 11369
    Prev
    Next
    INDEX
    Explanations

    concepts related to evasion or avoidance of regulations and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.02
    2:0.08
    3:0.15
    4:0.01
    5:0.03
    6:0.06
    7:0.07
    8:0.15
    9:0.19
    10:0.05
    11:0.13
    Negative Logits
    plates
    -1.26
    apsed
    -1.21
     yourselves
    -1.15
    MT
    -1.06
    gp
    -1.05
    ded
    -1.03
     Capacity
    -1.02
    psc
    -1.02
     Bild
    -1.00
    MET
    -1.00
    POSITIVE LOGITS
    assment
    1.27
     altogether
    1.25
     pesky
    1.25
     boredom
    1.11
    ourt
    1.08
     bounds
    1.07
    roach
    1.03
     foul
    1.01
    arsh
    1.01
     slightest
    1.00
    Activations Density 0.005%

    No Known Activations