© 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. 7322
    Prev
    Next
    INDEX
    Explanations

    phrasal structures related to importance or significance

    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
    0:0.01
    1:0.14
    2:0.10
    3:0.05
    4:0.01
    5:0.02
    6:0.06
    7:0.05
    8:0.09
    9:0.04
    10:0.06
    11:0.32
    Negative Logits
    reply
    -1.57
    repeat
    -1.40
     sqor
    -1.33
    evidence
    -1.21
    quit
    -1.20
    osponsors
    -1.19
    shapeshifter
    -1.19
    much
    -1.18
     lest
    -1.18
    conservancy
    -1.17
    POSITIVE LOGITS
     pier
    1.30
     Paw
    1.26
     cardboard
    1.14
     guiActiveUn
    1.14
     Peb
    1.13
    INA
    1.13
    ULAR
    1.09
    ICAL
    1.04
    ativity
    1.04
    �
    1.03
    Activations Density 0.035%

    No Known Activations