© 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. 2-ATT-KK
    11. 22065
    Prev
    Next
    INDEX
    Explanations

    references to collective entities or groups, particularly in political or economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.25
    3:0.09
    4:0.04
    5:0.06
    6:0.02
    7:0.01
    8:0.23
    9:0.12
    10:0.03
    11:0.02
    Negative Logits
    FORE
    -1.62
    yip
    -1.42
    gemony
    -1.32
    llor
    -1.20
    thora
    -1.20
    ukemia
    -1.19
    ufact
    -1.17
    asures
    -1.17
    lement
    -1.15
    terday
    -1.15
    POSITIVE LOGITS
     wedge
    1.40
     upd
    1.34
     wrench
    1.23
     trem
    1.19
     hither
    1.18
    eros
    1.17
     modem
    1.16
     uphill
    1.13
     ster
    1.11
     Auditor
    1.10
    Activations Density 0.016%

    No Known Activations