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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22627
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and governmental actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to specific types or forms of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.23
    3:0.04
    4:0.35
    5:0.04
    6:0.02
    7:0.02
    8:0.04
    9:0.08
    10:0.04
    11:0.02
    Negative Logits
     Noon
    -1.70
    sie
    -1.64
    listed
    -1.55
     Palest
    -1.54
    roy
    -1.52
    sey
    -1.46
     Sterling
    -1.41
     Redmond
    -1.40
     Sands
    -1.39
    ワ
    -1.34
    POSITIVE LOGITS
    ibus
    1.59
    ifice
    1.51
    lycer
    1.50
    oslav
    1.45
    ensional
    1.42
     antit
    1.41
     attic
    1.39
    ampunk
    1.34
     exorc
    1.32
    aucuses
    1.30
    Activations Density 0.017%

    No Known Activations