© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 9329
    Prev
    Next
    INDEX
    Explanations

    references to actions and states of individuals and organizations

    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
    1:0.32
    2:0.08
    3:0.02
    4:0.03
    5:0.12
    6:0.08
    7:0.06
    8:0.07
    9:0.05
    10:0.05
    11:0.06
    Negative Logits
    )'
    -1.93
    )."
    -1.86
    )--
    -1.64
    )—
    -1.62
    ').
    -1.57
    ),"
    -1.53
     cess
    -1.47
    …)
    -1.44
     punch
    -1.37
    )</
    -1.36
    POSITIVE LOGITS
    esta
    1.51
    Interested
    1.40
    abbit
    1.39
    ala
    1.34
     Fein
    1.34
    ardo
    1.33
    BuyableInstoreAndOnline
    1.33
    Indust
    1.32
    itsch
    1.31
    ecd
    1.29
    Activations Density 0.168%

    No Known Activations