© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10842
    Prev
    Next
    INDEX
    Explanations

    words related to appearance and visual descriptions

    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
    1:0.02
    2:0.05
    3:0.32
    4:0.02
    5:0.02
    6:0.25
    7:0.06
    8:0.04
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
     Frey
    -1.47
    の魔
    -1.33
    ワン
    -1.32
     appropri
    -1.22
     NCT
    -1.18
    stown
    -1.18
     ko
    -1.18
    committee
    -1.16
     reincarn
    -1.13
     emer
    -1.13
    POSITIVE LOGITS
    qt
    1.90
    ouse
    1.52
    thood
    1.51
    olate
    1.48
    cence
    1.48
    cies
    1.47
    nown
    1.43
    zona
    1.39
     Aires
    1.38
    ilus
    1.35
    Activations Density 0.021%

    No Known Activations