© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 29000
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or proper nouns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.08
    2:0.07
    3:0.04
    4:0.03
    5:0.13
    6:0.31
    7:0.02
    8:0.03
    9:0.10
    10:0.06
    11:0.04
    Negative Logits
    acebook
    -1.59
     drying
    -1.37
    ModLoader
    -1.36
    isSpecialOrderable
    -1.31
    APTER
    -1.20
     subscriptions
    -1.17
    Reviewed
    -1.16
    itably
    -1.16
     indoors
    -1.16
     sidewalks
    -1.16
    POSITIVE LOGITS
    �
    1.53
    �士
    1.49
    ��
    1.45
    lich
    1.44
    idy
    1.42
    �
    1.41
    ilon
    1.34
     Constantin
    1.32
    isl
    1.32
     himself
    1.31
    Activations Density 0.017%

    No Known Activations