© 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. 10817
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion or concern regarding situations and outcomes

    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
    1:0.13
    2:0.10
    3:0.02
    4:0.01
    5:0.07
    6:0.29
    7:0.06
    8:0.08
    9:0.05
    10:0.07
    11:0.04
    Negative Logits
     scree
    -1.34
     attendant
    -1.23
     Juven
    -1.13
     flourish
    -1.12
     respectively
    -1.10
     takeover
    -1.10
     spawned
    -1.09
     backdrop
    -1.07
     Collective
    -1.07
     itself
    -1.07
    POSITIVE LOGITS
    poke
    1.70
     myself
    1.38
    ascus
    1.32
    olit
    1.31
     personally
    1.30
    avascript
    1.30
    tta
    1.27
    lex
    1.18
     grap
    1.16
    extremely
    1.15
    Activations Density 0.233%

    No Known Activations