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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 110
    Prev
    Next
    INDEX
    Explanations

    language and phrases related to belief and opinion in sports contexts

    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
    0:0.19
    1:0.02
    2:0.15
    3:0.10
    4:0.02
    5:0.09
    6:0.03
    7:0.06
    8:0.18
    9:0.03
    10:0.05
    11:0.02
    Negative Logits
    CBC
    -3.80
    osponsors
    -3.04
     CBC
    -3.02
     Anchorage
    -3.01
    Canadian
    -2.96
     Dartmouth
    -2.93
    Canada
    -2.85
     Scotia
    -2.80
    Penn
    -2.77
     Alaska
    -2.76
    POSITIVE LOGITS
     Mourinho
    4.83
     Guardiola
    4.66
     Bayern
    3.98
     Gaal
    3.83
     Ronaldo
    3.58
    inho
    3.49
     Barcelona
    3.36
     Portuguese
    3.34
     Champions
    3.33
     Bundesliga
    3.22
    Activations Density 0.027%

    No Known Activations