© 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. 13203
    Prev
    Next
    INDEX
    Explanations

    text related to weights and measurements

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

    phrases and terms related to weight and measurements

    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
    0:0.04
    1:0.06
    2:0.07
    3:0.04
    4:0.04
    5:0.07
    6:0.06
    7:0.08
    8:0.06
    9:0.30
    10:0.09
    11:0.05
    Negative Logits
    lance
    -1.65
    vation
    -1.49
    anza
    -1.44
    iHUD
    -1.43
    nect
    -1.39
    exit
    -1.36
    Delete
    -1.30
    ��
    -1.29
    jection
    -1.29
    oche
    -1.26
    POSITIVE LOGITS
     weights
    1.64
     heaviest
    1.42
     weighs
    1.32
     Guinness
    1.29
     weigh
    1.26
     concess
    1.24
     trough
    1.21
     weighed
    1.18
     weighing
    1.18
     Pend
    1.17
    Activations Density 0.013%

    No Known Activations