© 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. 2-ATT-KK
    11. 21690
    Prev
    Next
    INDEX
    Explanations

    phrases and structures that indicate relationships or connections between subjects or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.04
    2:0.04
    3:0.05
    4:0.29
    5:0.11
    6:0.05
    7:0.04
    8:0.06
    9:0.09
    10:0.08
    11:0.03
    Negative Logits
     ballot
    -1.40
     circuit
    -1.38
     tamp
    -1.35
     distraction
    -1.32
    eln
    -1.31
     fumble
    -1.26
     gentleman
    -1.25
     persuasion
    -1.24
     handcuffs
    -1.20
     manoeuv
    -1.19
    POSITIVE LOGITS
     Coverage
    1.61
    sung
    1.33
    audi
    1.26
    ETH
    1.24
     SUPPORT
    1.24
    lycer
    1.24
     Supports
    1.23
     Shel
    1.22
    sbm
    1.21
    YR
    1.20
    Activations Density 0.213%

    No Known Activations