© 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. 9421
    Prev
    Next
    INDEX
    Explanations

    discussions of actions and decisions made by individuals in various contexts

    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
    1:0.07
    2:0.12
    3:0.03
    4:0.03
    5:0.07
    6:0.21
    7:0.12
    8:0.09
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    Higher
    -1.48
     interfering
    -1.48
     comprised
    -1.47
     Higher
    -1.47
     conducive
    -1.46
     millenn
    -1.46
    lihood
    -1.41
     circumstance
    -1.41
     populated
    -1.38
    romeda
    -1.37
    POSITIVE LOGITS
    �
    1.53
     herself
    1.46
    bart
    1.45
     Mane
    1.43
    bash
    1.43
    bra
    1.34
     Nanto
    1.34
     Bent
    1.34
    �
    1.33
    Tools
    1.33
    Activations Density 0.286%

    No Known Activations