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. 11016
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and positive emotional states

    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
    0:0.05
    1:0.02
    2:0.08
    3:0.22
    4:0.03
    5:0.05
    6:0.02
    7:0.06
    8:0.04
    9:0.02
    10:0.25
    11:0.10
    Negative Logits
     Hebdo
    -2.28
     infiltration
    -2.23
     manifests
    -2.13
     deeds
    -2.12
     manifested
    -2.08
     aborted
    -1.98
     inciner
    -1.96
     replicated
    -1.95
     killings
    -1.95
     exploits
    -1.95
    POSITIVE LOGITS
    �
    3.16
    sorry
    3.02
    ♥
    2.98
    �
    2.94
     thankful
    2.92
    ☆
    2.76
    ����
    2.75
     grateful
    2.73
    �
    2.73
    ★
    2.71
    Activations Density 0.074%

    No Known Activations