© 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. 5-ATT-KK
    11. 3128
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.12
    3:0.07
    4:0.10
    5:0.03
    6:0.26
    7:0.03
    8:0.07
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
     Rolling
    -1.38
     Marines
    -1.35
     pow
    -1.35
     Corps
    -1.34
     Alive
    -1.34
     Rocky
    -1.28
     ALEC
    -1.28
     Declaration
    -1.25
     virginity
    -1.25
     Corpse
    -1.24
    POSITIVE LOGITS
    etheless
    1.96
    urther
    1.69
    quant
    1.67
    theless
    1.53
    Downloadha
    1.49
    anwhile
    1.49
    heimer
    1.48
    peria
    1.43
    edge
    1.43
    imore
    1.42
    Activations Density 0.006%

    No Known Activations