© 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. 6751
    Prev
    Next
    INDEX
    Explanations

    phrases that involve the concept of expectation or anticipation

    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
    1:0.01
    2:0.13
    3:0.20
    4:0.01
    5:0.02
    6:0.04
    7:0.13
    8:0.11
    9:0.15
    10:0.06
    11:0.10
    Negative Logits
     Matter
    -1.06
     lineback
    -1.01
    aple
    -0.98
     flagged
    -0.97
     Blumenthal
    -0.96
    ilaterally
    -0.95
     Lois
    -0.94
     Arpaio
    -0.94
    aroo
    -0.94
    Mine
    -0.94
    POSITIVE LOGITS
    results
    1.31
    inen
    1.15
    NULL
    1.10
     reactions
    1.10
     fulfillment
    1.08
    SpaceEngineers
    1.06
     ut
    1.04
    iHUD
    1.04
    wcsstore
    1.03
     results
    1.03
    Activations Density 0.027%

    No Known Activations