© 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. 8977
    Prev
    Next
    INDEX
    Explanations

    words indicating social groups or collective identities

    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
    0:0.02
    1:0.03
    2:0.08
    3:0.03
    4:0.02
    5:0.07
    6:0.20
    7:0.31
    8:0.05
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     analogy
    -1.36
    Matrix
    -1.35
     gradient
    -1.34
     breakthrough
    -1.32
     iterations
    -1.30
     accompan
    -1.29
    ァ
    -1.29
     matrix
    -1.24
    BIT
    -1.21
     iteration
    -1.21
    POSITIVE LOGITS
     Liberties
    1.47
    cair
    1.44
    pees
    1.42
    doms
    1.38
    cius
    1.37
    joice
    1.31
    vernment
    1.28
     Militia
    1.26
     Rebell
    1.25
    owe
    1.25
    Activations Density 0.055%

    No Known Activations