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. 3209
    Prev
    Next
    INDEX
    Explanations

    structures and elements of reports or analytical documents

    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
    0:0.14
    1:0.02
    2:0.07
    3:0.14
    4:0.04
    5:0.05
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.37
    11:0.03
    Negative Logits
    urch
    -2.02
    "]=>
    -1.87
     lifelong
    -1.87
     Flavoring
    -1.86
     everyday
    -1.85
    amping
    -1.79
     anymore
    -1.78
     wherever
    -1.75
    growing
    -1.74
     Younger
    -1.72
    POSITIVE LOGITS
     summarizes
    3.54
     describes
    3.43
     outlines
    3.40
     contains
    3.32
     specifies
    3.18
     mentions
    3.17
     illustrates
    3.04
     depicts
    3.02
     indicates
    3.02
     relates
    2.98
    Activations Density 0.329%

    No Known Activations