© 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. 12814
    Prev
    Next
    INDEX
    Explanations

    names of people, especially with mentions of injuries or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to individuals named Ben in various contexts

    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
    0:0.04
    1:0.04
    2:0.14
    3:0.06
    4:0.03
    5:0.04
    6:0.20
    7:0.18
    8:0.06
    9:0.05
    10:0.08
    11:0.04
    Negative Logits
    pert
    -1.22
     coefficients
    -1.12
    isSpecialOrderable
    -1.11
     vibrations
    -1.06
     refunds
    -1.06
    etheless
    -1.04
    shots
    -1.03
     practitioners
    -1.03
    cipline
    -1.02
    effects
    -1.01
    POSITIVE LOGITS
    �士
    1.38
    pictured
    1.30
     Pru
    1.22
    assian
    1.21
    heimer
    1.21
    SON
    1.20
    ithe
    1.20
    eely
    1.17
    zeb
    1.15
    HAM
    1.12
    Activations Density 0.017%

    No Known Activations