© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43121
    Prev
    Next
    INDEX
    Explanations

    prepositions and temporal language indicating ongoing actions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.15
    3:0.07
    4:0.13
    5:0.02
    6:0.39
    7:0.03
    8:0.02
    9:0.02
    10:0.03
    11:0.04
    Negative Logits
    DB
    -1.47
     Flavoring
    -1.43
    utenberg
    -1.40
    Save
    -1.40
    TEXTURE
    -1.37
    afia
    -1.32
    RAM
    -1.30
    ella
    -1.29
    Status
    -1.26
    amar
    -1.25
    POSITIVE LOGITS
    theless
    1.90
    cause
    1.50
    etheless
    1.44
     Ples
    1.42
     wise
    1.41
    ovych
    1.40
     garn
    1.37
    iHUD
    1.35
    handedly
    1.35
    pite
    1.32
    Activations Density 0.106%

    No Known Activations