© 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. 12542
    Prev
    Next
    INDEX
    Explanations

    words related to space exploration and equipment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    details related to environmental conditions and materials

    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
    1:0.03
    2:0.05
    3:0.04
    4:0.04
    5:0.08
    6:0.07
    7:0.39
    8:0.05
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    actionDate
    -1.52
     successors
    -1.45
    IX
    -1.42
    ゴン
    -1.33
    ��
    -1.31
    omics
    -1.29
    puter
    -1.27
     principled
    -1.23
    hess
    -1.19
    iscopal
    -1.18
    POSITIVE LOGITS
     contamin
    1.60
     haze
    1.48
     drown
    1.43
     harvesting
    1.39
     pollen
    1.39
     flooding
    1.39
     swirl
    1.37
    ioxide
    1.37
     contam
    1.36
     grains
    1.36
    Activations Density 0.188%

    No Known Activations