© 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. 13588
    Prev
    Next
    INDEX
    Explanations

    strong emotional or impactful adjectives and nouns

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

    elements related to criticism and commentary

    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
    0:0.03
    1:0.03
    2:0.06
    3:0.04
    4:0.02
    5:0.04
    6:0.08
    7:0.11
    8:0.05
    9:0.04
    10:0.07
    11:0.37
    Negative Logits
    venants
    -1.55
     Lumpur
    -1.45
     occupation
    -1.34
     Loft
    -1.32
    Initialized
    -1.31
    essions
    -1.29
     authorised
    -1.25
    CLUD
    -1.23
     Theatre
    -1.22
    otiation
    -1.22
    POSITIVE LOGITS
    BIP
    1.47
     slug
    1.26
     kicker
    1.23
     envy
    1.23
     nonetheless
    1.18
     aspirin
    1.18
     pes
    1.17
     sunscreen
    1.16
     blot
    1.15
     Dragonbound
    1.14
    Activations Density 0.134%

    No Known Activations