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. 11441
    Prev
    Next
    INDEX
    Explanations

    prominent names and titles in the context of entertainment and legal matters

    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
    0:0.12
    1:0.07
    2:0.05
    3:0.05
    4:0.03
    5:0.04
    6:0.26
    7:0.03
    8:0.05
    9:0.18
    10:0.03
    11:0.04
    Negative Logits
     ►
    -3.88
     Riy
    -3.79
     Maz
    -3.57
     tigers
    -3.52
    pas
    -3.47
    eva
    -3.36
     tiger
    -3.31
     dj
    -3.31
     tot
    -3.29
     Jag
    -3.27
    POSITIVE LOGITS
     Broad
    8.75
    Broad
    8.19
    broad
    6.11
     broadband
    4.28
     Broadcast
    4.27
     Burst
    4.18
    arrow
    4.09
     bandwidth
    4.05
     Wide
    3.99
     Bow
    3.94
    Activations Density 0.001%

    No Known Activations