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. 3103
    Prev
    Next
    INDEX
    Explanations

    phrases related to public statements and comments made by individuals, particularly politicians

    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
    0:0.38
    1:0.02
    2:0.17
    3:0.09
    4:0.03
    5:0.08
    6:0.02
    7:0.04
    8:0.02
    9:0.03
    10:0.05
    11:0.01
    Negative Logits
    finder
    -2.83
    itaire
    -2.35
    emis
    -2.32
    modules
    -2.23
    ventures
    -2.22
    Task
    -2.14
    Setup
    -2.11
     filesystem
    -2.10
     Trials
    -2.06
    asus
    -2.05
    POSITIVE LOGITS
     uttered
    4.12
     comments
    3.87
     remarks
    3.71
     phr
    3.53
     slurs
    3.48
     remark
    3.46
     comment
    3.35
     statements
    3.30
     words
    3.28
     tir
    3.18
    Activations Density 0.474%

    No Known Activations