© 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. 5224
    Prev
    Next
    INDEX
    Explanations

    indications of errors and methods to retrieve error information, especially in programming contexts

    oai_token-act-pair · gpt-3.5-turbo
    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
    0:0.03
    1:0.04
    2:0.06
    3:0.09
    4:0.03
    5:0.06
    6:0.10
    7:0.29
    8:0.07
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
    igham
    -1.33
    soDeliveryDate
    -1.30
    angelo
    -1.26
    illac
    -1.24
    interstitial
    -1.22
    龍喚士
    -1.19
    uxe
    -1.11
    ustom
    -1.09
    utical
    -1.08
     nude
    -1.06
    POSITIVE LOGITS
     entropy
    1.12
     Gibbs
    1.05
     msec
    1.03
     Niet
    1.01
     Compensation
    1.00
     severity
    0.99
     ppm
    0.99
     incurred
    0.99
     parsing
    0.98
     milliseconds
    0.98
    Activations Density 0.049%

    No Known Activations