Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 16
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their actions or influence regarding societal or historical issues

    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
    0:0.07
    1:0.02
    2:0.07
    3:0.03
    4:0.05
    5:0.04
    6:0.24
    7:0.05
    8:0.05
    9:0.29
    10:0.02
    11:0.03
    Negative Logits
    leigh
    -3.92
    stal
    -3.69
    ��
    -3.59
     buckle
    -3.55
     Weld
    -3.48
    lie
    -3.41
    Knight
    -3.41
     Wyn
    -3.40
    oult
    -3.40
     Rhode
    -3.38
    POSITIVE LOGITS
     Ap
    9.36
    Ap
    8.15
     ap
    6.55
    ap
    5.73
     Sap
    5.61
     Kap
    5.30
     apes
    5.11
     Pap
    5.02
     Apocalypse
    4.92
    apo
    4.91
    Activations Density 0.005%

    No Known Activations