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. 31
    Prev
    Next
    INDEX
    Explanations

    dialogue or statements related to personal experiences or anecdotes

    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
    0:0.03
    1:0.12
    2:0.05
    3:0.08
    4:0.16
    5:0.08
    6:0.05
    7:0.20
    8:0.04
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    覚醒
    -2.78
     awaits
    -2.56
     exting
    -2.46
     conduc
    -2.37
    黒
    -2.33
     strives
    -2.31
    xit
    -2.29
    erenn
    -2.23
    arest
    -2.23
    iosyncr
    -2.22
    POSITIVE LOGITS
    Yeah
    3.87
     everybody
    3.43
    laughs
    3.40
     yeah
    3.31
     stuff
    3.30
    Anyway
    3.23
    Laughs
    3.23
     Yeah
    3.22
     somebody
    3.22
    And
    3.21
    Activations Density 0.522%

    No Known Activations