© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 14398
    Prev
    Next
    INDEX
    Explanations

    sensory-related words such as "sensor," "camera," "data," and "tracking."

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to various sensors and their functionalities in technology

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.10
    4:0.03
    5:0.06
    6:0.09
    7:0.36
    8:0.05
    9:0.03
    10:0.06
    11:0.07
    Negative Logits
    INGTON
    -1.34
     Ruins
    -1.33
    ardless
    -1.32
     unfinished
    -1.30
     Disneyland
    -1.29
     Struggle
    -1.29
    --------------------------------------------------------
    -1.28
    erest
    -1.23
     celebration
    -1.22
     SHARES
    -1.20
    POSITIVE LOGITS
     detects
    1.49
     pse
    1.40
     predictive
    1.32
    atis
    1.31
     detect
    1.26
    enabled
    1.25
    agraph
    1.23
    oven
    1.20
     monitors
    1.18
     alerts
    1.17
    Activations Density 0.064%

    No Known Activations