© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11688
    Prev
    Next
    INDEX
    Explanations

    questions or statements expressing uncertainty or calling for clarification

    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
    0:0.01
    1:0.06
    2:0.11
    3:0.13
    4:0.02
    5:0.02
    6:0.08
    7:0.09
    8:0.10
    9:0.07
    10:0.07
    11:0.18
    Negative Logits
    apixel
    -1.26
    uther
    -1.06
     ILCS
    -1.03
    uania
    -0.99
    iasm
    -0.92
     QC
    -0.91
    pict
    -0.91
    raltar
    -0.89
    alions
    -0.89
    evidence
    -0.88
    POSITIVE LOGITS
    ukong
    1.05
     differs
    1.04
    セ
    1.02
    ギ
    0.99
    Reviewer
    0.99
    ?]
    0.98
    Decre
    0.97
     differ
    0.97
     tamp
    0.96
    Magikarp
    0.95
    Activations Density 0.029%

    No Known Activations