© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 14335
    Prev
    Next
    INDEX
    Explanations

    mentions of issues or observations related to bags

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

    references to bags and boxes, particularly in the context of packaging and storage items

    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
    0:0.31
    1:0.03
    2:0.04
    3:0.07
    4:0.08
    5:0.06
    6:0.07
    7:0.07
    8:0.04
    9:0.04
    10:0.10
    11:0.05
    Negative Logits
    peace
    -1.52
     Spectrum
    -1.39
     bloom
    -1.23
    ukemia
    -1.23
    ����
    -1.22
    nesota
    -1.21
    stru
    -1.20
    onomous
    -1.18
    tra
    -1.16
    Alert
    -1.14
    POSITIVE LOGITS
     lid
    1.56
    holders
    1.50
     shelves
    1.45
     liner
    1.45
     cabinets
    1.41
     shipments
    1.39
    Accessory
    1.38
    utters
    1.38
    holder
    1.37
     containing
    1.36
    Activations Density 0.032%

    No Known Activations