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. 18
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and their accomplishments

    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
    •Attn Out Feature List

    No Comments

    Head Attr Weights
    0:0.03
    1:0.50
    2:0.03
    3:0.05
    4:0.03
    5:0.07
    6:0.04
    7:0.03
    8:0.03
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    acs
    -2.87
     someday
    -2.54
    アル
    -2.53
     Sloven
    -2.46
    option
    -2.42
     achievable
    -2.35
     Cooke
    -2.34
    isson
    -2.33
     Courage
    -2.27
     Sao
    -2.26
    POSITIVE LOGITS
     17
    4.45
    17
    4.39
    18
    3.44
     18
    3.44
    eteenth
    3.38
     eighteenth
    3.27
     1700
    3.20
     16
    3.13
    eteen
    3.13
    uko
    3.12
    Activations Density 0.008%

    No Known Activations