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. 22082
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage in context

    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
    0:0.07
    1:0.04
    2:0.04
    3:0.06
    4:0.03
    5:0.06
    6:0.09
    7:0.14
    8:0.05
    9:0.04
    10:0.21
    11:0.11
    Negative Logits
     notwithstanding
    -0.95
    FTWARE
    -0.94
     DRAG
    -0.90
    theless
    -0.80
     alike
    -0.79
    ="#
    -0.79
    enegger
    -0.75
     mentality
    -0.74
     therein
    -0.74
     vibe
    -0.73
    POSITIVE LOGITS
    龍喚士
    0.86
    sych
    0.81
    hs
    0.79
     Beck
    0.78
     Ep
    0.78
    ho
    0.75
    lus
    0.75
     Jere
    0.75
    rak
    0.74
    hung
    0.73
    Activations Density 0.270%

    No Known Activations