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. 3083
    Prev
    Next
    INDEX
    Explanations

    occurrences of dialogue and reporting verbs in the text

    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
    0:0.11
    1:0.02
    2:0.05
    3:0.02
    4:0.05
    5:0.04
    6:0.24
    7:0.05
    8:0.06
    9:0.23
    10:0.03
    11:0.04
    Negative Logits
    ouri
    -3.69
    vir
    -3.54
     Venezuelan
    -3.53
     Venezuel
    -3.50
    Nic
    -3.44
    uri
    -3.42
     Haitian
    -3.41
     Yuan
    -3.32
     Nora
    -3.31
     Imper
    -3.28
    POSITIVE LOGITS
     Beck
    11.41
    Beck
    10.49
     Becky
    5.60
     Baz
    4.65
     Glenn
    4.58
    beck
    4.56
     Hanson
    4.20
     Wink
    4.15
     Brewer
    4.14
    band
    4.12
    Activations Density 0.007%

    No Known Activations