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. 3162
    Prev
    Next
    INDEX
    Explanations

    references to history and ecclesiastical contexts

    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
    0:0.03
    1:0.03
    2:0.02
    3:0.07
    4:0.18
    5:0.05
    6:0.38
    7:0.03
    8:0.02
    9:0.02
    10:0.05
    11:0.05
    Negative Logits
     Sched
    -3.03
     Qian
    -3.01
     Fundamental
    -3.00
    Motor
    -2.94
     IPM
    -2.78
     Migration
    -2.78
    ngth
    -2.78
     Rac
    -2.75
     Por
    -2.74
     Riding
    -2.71
    POSITIVE LOGITS
     dispensary
    3.29
     Dex
    3.21
     lum
    3.10
     Dexter
    3.00
     dispensaries
    2.95
    Dex
    2.82
     edit
    2.79
     Holo
    2.76
     Hazel
    2.75
    notations
    2.75
    Activations Density 0.022%

    No Known Activations