© 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. 22060
    Prev
    Next
    INDEX
    Explanations

    terms related to development, education, and organizational structures

    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
    0:0.04
    1:0.01
    2:0.05
    3:0.17
    4:0.02
    5:0.08
    6:0.02
    7:0.11
    8:0.04
    9:0.05
    10:0.23
    11:0.11
    Negative Logits
    uba
    -0.84
    ucl
    -0.83
    ornings
    -0.82
    �
    -0.80
    unte
    -0.76
    imon
    -0.75
    wic
    -0.75
    anta
    -0.74
    cpp
    -0.74
    icy
    -0.73
    POSITIVE LOGITS
    liest
    1.17
    iest
    1.04
    forts
    1.01
    hest
    1.00
    osphere
    0.96
     portion
    0.95
     bandwagon
    0.91
     fallacy
    0.91
     fraternity
    0.86
     Mysteries
    0.83
    Activations Density 2.170%

    No Known Activations