© 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. 11627
    Prev
    Next
    INDEX
    Explanations

    words related to emotions or states of being

    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
    0:0.05
    1:0.05
    2:0.09
    3:0.20
    4:0.04
    5:0.06
    6:0.07
    7:0.11
    8:0.09
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    utical
    -1.20
    ��
    -1.19
    glers
    -1.17
    ibly
    -1.16
    ahon
    -1.14
    ealous
    -1.12
    onge
    -1.09
    undai
    -1.09
    ipedia
    -1.08
    ailability
    -1.07
    POSITIVE LOGITS
     ®
    1.15
     Appears
    1.06
    バ
    1.01
     illum
    1.00
    ……
    0.98
     PUR
    0.97
    プ
    0.95
     Forth
    0.93
     �
    0.93
    roy
    0.93
    Activations Density 0.004%

    No Known Activations