© 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. 8074
    Prev
    Next
    INDEX
    Explanations

    concepts related to classification and categorization

    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
    1:0.04
    2:0.16
    3:0.09
    4:0.01
    5:0.04
    6:0.13
    7:0.10
    8:0.10
    9:0.06
    10:0.09
    11:0.10
    Negative Logits
     Osw
    -1.06
    abad
    -0.96
     prophetic
    -0.91
     Rehab
    -0.86
    Dialogue
    -0.85
    ⓘ
    -0.81
     Ped
    -0.80
     Guru
    -0.80
     Zoro
    -0.79
     deaf
    -0.79
    POSITIVE LOGITS
    bucks
    1.09
    NBA
    1.08
    licks
    1.03
    axy
    0.99
    ighters
    0.97
    usable
    0.97
     @@
    0.97
    akeru
    0.96
     WITHOUT
    0.95
    grain
    0.94
    Activations Density 0.444%

    No Known Activations