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

    Neuronpedia

    APICircuit 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. 7617
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or appreciation towards others

    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
    0:0.36
    1:0.01
    2:0.02
    3:0.11
    4:0.13
    5:0.08
    6:0.01
    7:0.03
    8:0.12
    9:0.01
    10:0.04
    11:0.02
    Negative Logits
     meanings
    -2.59
    ellation
    -2.53
     paraph
    -2.48
     congr
    -2.35
     opin
    -2.32
     declass
    -2.31
     praises
    -2.25
     watered
    -2.23
    ":["
    -2.23
    irie
    -2.22
    POSITIVE LOGITS
     Bagg
    2.67
    Dash
    2.67
    raud
    2.57
    vertising
    2.57
    CTV
    2.54
    cgi
    2.51
     Gum
    2.46
    utenberg
    2.45
    TPS
    2.39
    tube
    2.35
    Activations Density 0.005%

    No Known Activations