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. 11284
    Prev
    Next
    INDEX
    Explanations

    significant actions and relationships involving people in various 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
    0:0.04
    1:0.03
    2:0.06
    3:0.23
    4:0.02
    5:0.07
    6:0.02
    7:0.05
    8:0.03
    9:0.02
    10:0.37
    11:0.03
    Negative Logits
    same
    -2.55
    ��
    -2.46
    ��
    -2.40
     unfocusedRange
    -2.31
    ��
    -2.27
    �
    -2.25
    �
    -2.15
    �
    -2.10
    �
    -2.08
    �
    -2.07
    POSITIVE LOGITS
     hardest
    2.76
     heaviest
    2.56
     brunt
    2.50
     greatest
    2.34
    "]=>
    2.21
    cest
    2.21
     decisive
    2.12
    alys
    2.10
     shine
    2.10
     happiest
    2.10
    Activations Density 0.182%

    No Known Activations