© 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. 3-ATT-KK
    11. 6580
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to threats or danger

    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
    0:0.03
    1:0.03
    2:0.10
    3:0.29
    4:0.03
    5:0.03
    6:0.17
    7:0.08
    8:0.04
    9:0.02
    10:0.09
    11:0.04
    Negative Logits
     mot
    -1.30
    768
    -1.19
     secrets
    -1.15
     Magicka
    -1.15
     obstacles
    -1.14
     answ
    -1.13
     counsel
    -1.12
     Secrets
    -1.10
     Prelude
    -1.10
     confession
    -1.09
    POSITIVE LOGITS
    sel
    1.56
    illon
    1.44
    nel
    1.38
    oro
    1.35
    rika
    1.35
    eous
    1.32
    umatic
    1.30
    ese
    1.30
    sels
    1.30
    ippi
    1.29
    Activations Density 0.010%

    No Known Activations