© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11854
    Prev
    Next
    INDEX
    Explanations

    terms related to plans, updates, and official documents

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

    phrases related to updates or revisions in policies or documents

    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
    0:0.03
    1:0.04
    2:0.07
    3:0.02
    4:0.02
    5:0.07
    6:0.08
    7:0.10
    8:0.05
    9:0.03
    10:0.09
    11:0.35
    Negative Logits
    ongyang
    -1.27
    ometimes
    -1.24
     Pigs
    -1.22
    cott
    -1.16
     神
    -1.14
    assadors
    -1.14
    ihad
    -1.14
    frey
    -1.12
    ophob
    -1.11
    odan
    -1.11
    POSITIVE LOGITS
     Revised
    1.35
    catentry
    1.34
     edition
    1.34
     version
    1.31
     revised
    1.30
     Version
    1.26
     revisions
    1.26
    PDATED
    1.20
     methodology
    1.19
     editions
    1.17
    Activations Density 0.055%

    No Known Activations