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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11155
    Prev
    Next
    INDEX
    Explanations

    references to famous artists and their works

    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
    0:0.31
    1:0.02
    2:0.08
    3:0.09
    4:0.03
    5:0.11
    6:0.04
    7:0.08
    8:0.07
    9:0.05
    10:0.05
    11:0.01
    Negative Logits
    odcast
    -3.76
     podcasts
    -3.73
     Podcast
    -3.30
     podcast
    -3.18
    YouTube
    -2.87
     Flavoring
    -2.82
     Webs
    -2.56
     Startup
    -2.56
    infeld
    -2.54
     Hulu
    -2.45
    POSITIVE LOGITS
     painted
    4.09
     portrait
    4.03
     painter
    4.02
     portraits
    3.92
     painting
    3.88
     paintings
    3.83
     depicting
    3.48
     Painter
    3.43
    painted
    3.30
     gloomy
    3.16
    Activations Density 0.018%

    No Known Activations