© 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 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. 1494
    Prev
    Next
    INDEX
    Explanations

    mentions of conversations and interactions, particularly in community contexts

    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
    0:0.02
    1:0.02
    2:0.30
    3:0.13
    4:0.12
    5:0.04
    6:0.03
    7:0.09
    8:0.04
    9:0.04
    10:0.08
    11:0.04
    Negative Logits
    \.
    -1.45
    genre
    -1.38
     Fernand
    -1.34
    ゴ
    -1.28
     Bees
    -1.24
    cham
    -1.24
    ynt
    -1.24
    ilon
    -1.23
    %);
    -1.23
     advances
    -1.22
    POSITIVE LOGITS
     someday
    1.60
     ASAP
    1.49
     permanently
    1.48
     surg
    1.47
     ready
    1.46
     uninterrupted
    1.44
     functioning
    1.42
    awi
    1.41
    iphany
    1.40
     unrestricted
    1.40
    Activations Density 0.169%

    No Known Activations