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. 18776
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or expressions of dissatisfaction

    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
    2:0.04
    3:0.15
    4:0.05
    5:0.12
    6:0.03
    7:0.23
    8:0.03
    9:0.02
    10:0.09
    11:0.05
    Negative Logits
    quote
    -2.13
    ][/
    -2.03
     DPR
    -1.98
     confirm
    -1.95
     timeline
    -1.92
     confirmation
    -1.92
     xml
    -1.92
    ebin
    -1.90
     Cyr
    -1.88
    >[
    -1.86
    POSITIVE LOGITS
     thirty
    3.03
     twenty
    2.93
    Twenty
    2.88
    ixty
    2.84
     seventeen
    2.82
     fifteen
    2.78
    seven
    2.77
     fifty
    2.73
    Thirty
    2.72
     fourteen
    2.65
    Activations Density 0.002%

    No Known Activations