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. 10678
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts related to actions being done "by" someone or something

    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
    0:0.04
    1:0.18
    2:0.07
    3:0.16
    4:0.05
    5:0.07
    6:0.04
    7:0.09
    8:0.03
    9:0.12
    10:0.07
    11:0.03
    Negative Logits
     Newsletter
    -2.75
    laughter
    -2.75
    Fax
    -2.66
    other
    -2.63
    SHARE
    -2.60
     Other
    -2.60
    employment
    -2.57
     SERVICES
    -2.56
    BT
    -2.52
    Russ
    -2.50
    POSITIVE LOGITS
     distingu
    2.50
    ulia
    2.45
     //[
    2.42
     seams
    2.33
     lantern
    2.33
    anyon
    2.31
     comprom
    2.28
     embr
    2.27
    onso
    2.27
    aily
    2.26
    Activations Density 0.001%

    No Known Activations