© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14750
    Prev
    Next
    INDEX
    Explanations

    the presence of institutions or organizations in relevant contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.25
    2:0.06
    3:0.08
    4:0.03
    5:0.01
    6:0.14
    7:0.11
    8:0.02
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
    riv
    -2.38
    Premium
    -2.32
    gram
    -2.27
    ago
    -2.21
     waterproof
    -2.21
     recomm
    -2.19
     Schiff
    -2.16
    lly
    -2.16
     mortg
    -2.15
    wagen
    -2.14
    POSITIVE LOGITS
     center
    6.46
     Center
    5.83
    center
    5.75
    Center
    5.47
     centers
    5.46
     centre
    5.06
     CENT
    4.86
     Centre
    4.86
    Cent
    4.80
     Centers
    4.28
    Activations Density 0.036%

    No Known Activations