© 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. 8164
    Prev
    Next
    INDEX
    Explanations

    rankings and placements related to competitions or tournaments

    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
    0:0.02
    1:0.03
    2:0.06
    3:0.07
    4:0.02
    5:0.07
    6:0.06
    7:0.27
    8:0.05
    9:0.07
    10:0.10
    11:0.13
    Negative Logits
    ivation
    -1.36
    DragonMagazine
    -1.31
    ahu
    -1.26
    wig
    -1.23
    tics
    -1.22
    romy
    -1.21
    bj
    -1.20
    aea
    -1.20
    leep
    -1.19
    ichick
    -1.19
    POSITIVE LOGITS
     standings
    1.37
     relegation
    1.32
     Guinness
    1.31
     DISTRICT
    1.28
    ANA
    1.20
     championship
    1.18
     rankings
    1.17
     clearance
    1.16
    AMI
    1.14
     Dillon
    1.14
    Activations Density 0.018%

    No Known Activations