© 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. 14136
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or seeking specific information or opportunities

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

    references to the concept of searching or search activities

    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
    0:0.06
    1:0.03
    2:0.09
    3:0.03
    4:0.03
    5:0.06
    6:0.26
    7:0.07
    8:0.04
    9:0.08
    10:0.13
    11:0.08
    Negative Logits
    SPONSORED
    -1.25
    reed
    -1.21
     todd
    -1.19
    VERTISEMENT
    -1.11
    三
    -1.11
     Gentleman
    -1.08
    ��
    -1.07
    )",
    -1.06
    ocide
    -1.03
     Carbuncle
    -1.03
    POSITIVE LOGITS
    dylib
    1.37
    paralle
    1.27
     responders
    1.20
    cells
    1.14
    FTWARE
    1.12
    params
    1.11
     algorithms
    1.09
    gap
    1.07
     predictive
    1.06
    hap
    1.05
    Activations Density 0.009%

    No Known Activations