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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43734
    Prev
    Next
    INDEX
    Explanations

    pronouns and terms referring to individuals and specific entities

    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
    1:0.01
    2:0.12
    3:0.16
    4:0.28
    5:0.04
    6:0.05
    7:0.08
    8:0.04
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
    BuyableInstoreAndOnline
    -1.98
    20439
    -1.80
    Downloadha
    -1.79
     Pwr
    -1.60
    assetsadobe
    -1.60
    MET
    -1.50
     mathemat
    -1.45
    ��
    -1.44
    wcsstore
    -1.44
    inventoryQuantity
    -1.42
    POSITIVE LOGITS
    ?:
    1.66
    ?
    1.53
    án
    1.44
    .?
    1.43
    ?'
    1.42
    ?),
    1.41
    ?)
    1.39
    )?
    1.38
    ?,
    1.34
    ?).
    1.33
    Activations Density 0.072%

    No Known Activations