© 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. 9-ATT-KK
    11. 3654
    Prev
    Next
    INDEX
    Explanations

    commands or requests related to removing content or accessing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.24
    2:0.05
    3:0.12
    4:0.07
    5:0.09
    6:0.08
    7:0.06
    8:0.03
    9:0.10
    10:0.04
    11:0.04
    Negative Logits
    cffff
    -2.48
    iliated
    -2.40
     sclerosis
    -2.27
     guaranteed
    -2.27
     sized
    -2.18
     biggest
    -2.17
    ��
    -2.16
     isolated
    -2.14
    Little
    -2.11
    CI
    -2.08
    POSITIVE LOGITS
     ours
    3.13
     yours
    2.73
    them
    2.60
    hew
    2.55
    eva
    2.54
    gamer
    2.50
     us
    2.46
     thee
    2.45
    ß
    2.45
    luster
    2.43
    Activations Density 0.001%

    No Known Activations