© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 13630
    Prev
    Next
    INDEX
    Explanations

    words related to sports events and competitions, particularly focusing on specific actions and outcomes

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

    words and phrases that indicate appreciation or nostalgia

    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
    1:0.02
    2:0.11
    3:0.29
    4:0.01
    5:0.02
    6:0.04
    7:0.10
    8:0.08
    9:0.17
    10:0.04
    11:0.06
    Negative Logits
     thanking
    -1.10
    ilst
    -1.09
     phosphate
    -1.08
    tering
    -1.06
    anting
    -1.06
    Cry
    -1.06
    theless
    -1.05
    TOP
    -1.04
    church
    -1.03
     Conversation
    -1.02
    POSITIVE LOGITS
     Cth
    1.29
     Miko
    1.22
    bley
    1.19
    BILL
    1.18
    oslav
    1.18
    anka
    1.18
     cues
    1.17
    ById
    1.12
    abwe
    1.12
    aryn
    1.10
    Activations Density 0.043%

    No Known Activations