© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10673
    Prev
    Next
    INDEX
    Explanations

    connections between objects and their surroundings in a narrative context

    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
    1:0.03
    2:0.14
    3:0.03
    4:0.06
    5:0.11
    6:0.07
    7:0.17
    8:0.08
    9:0.04
    10:0.10
    11:0.07
    Negative Logits
    ennial
    -1.21
     campaigns
    -1.18
    racial
    -1.14
     nutshell
    -1.12
    polit
    -1.11
     endorsements
    -1.11
    olitical
    -1.10
     Disclosure
    -1.09
    ertain
    -1.07
    oyal
    -1.07
    POSITIVE LOGITS
     furiously
    1.39
     entrances
    1.38
     frantically
    1.34
     driveway
    1.31
     whence
    1.30
    ifice
    1.29
    asionally
    1.29
     angrily
    1.27
     drainage
    1.26
     entrance
    1.24
    Activations Density 0.269%

    No Known Activations