© 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. 2-ATT-KK
    11. 14384
    Prev
    Next
    INDEX
    Explanations

    verbs related to yielding or giving in to a particular influence

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.05
    1:0.03
    2:0.12
    3:0.06
    4:0.14
    5:0.04
    6:0.03
    7:0.03
    8:0.25
    9:0.12
    10:0.05
    11:0.02
    Negative Logits
    soDeliveryDate
    -1.76
    ERSON
    -1.36
     compares
    -1.30
    emouth
    -1.24
    angular
    -1.24
    liest
    -1.20
    arers
    -1.20
    bourg
    -1.18
    rians
    -1.18
     Mexicans
    -1.17
    POSITIVE LOGITS
     exhaustion
    1.70
    MpServer
    1.45
    unal
    1.42
    =~=~
    1.30
    geoning
    1.30
    ategory
    1.26
     Runtime
    1.26
    ioxide
    1.26
     tremend
    1.25
     sqor
    1.22
    Activations Density 0.002%

    No Known Activations