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. 3071
    Prev
    Next
    INDEX
    Explanations

    information related to organizational structure and regulatory frameworks

    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
    0:0.10
    1:0.07
    2:0.06
    3:0.06
    4:0.03
    5:0.04
    6:0.22
    7:0.04
    8:0.03
    9:0.23
    10:0.04
    11:0.03
    Negative Logits
     Interstellar
    -4.02
     Jack
    -3.68
     JACK
    -3.68
     Onion
    -3.64
    Jack
    -3.63
     HOR
    -3.53
     Astro
    -3.46
     marg
    -3.41
    Hor
    -3.27
     Alic
    -3.26
    POSITIVE LOGITS
     Practice
    6.29
     practice
    5.99
    practice
    5.79
     practices
    5.33
     practise
    5.14
     practiced
    5.02
     practicing
    4.96
    Pract
    4.82
     pract
    4.65
     Practices
    4.60
    Activations Density 0.004%

    No Known Activations