© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 10715
    Prev
    Next
    INDEX
    Explanations

    names of athletes or notable individuals involved in sports

    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
    0:0.04
    1:0.05
    2:0.09
    3:0.26
    4:0.03
    5:0.03
    6:0.11
    7:0.12
    8:0.04
    9:0.08
    10:0.05
    11:0.05
    Negative Logits
    etheless
    -1.46
    seless
    -1.45
    yip
    -1.45
    dfx
    -1.45
    theless
    -1.30
    perty
    -1.24
    ancies
    -1.23
    cffff
    -1.22
    idays
    -1.18
    arine
    -1.18
    POSITIVE LOGITS
    aman
    1.25
    izza
    1.22
    Vill
    1.20
    vez
    1.18
    Clar
    1.13
     Niño
    1.10
    覚醒
    1.10
     Vend
    1.09
    imov
    1.09
    izo
    1.09
    Activations Density 0.004%

    No Known Activations