© 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. 28329
    Prev
    Next
    INDEX
    Explanations

    references to family and social connections

    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
    0:0.10
    1:0.01
    2:0.19
    3:0.06
    4:0.07
    5:0.03
    6:0.09
    7:0.04
    8:0.14
    9:0.04
    10:0.07
    11:0.11
    Negative Logits
    boa
    -1.47
     moth
    -1.45
    opa
    -1.44
    ctory
    -1.34
    ��
    -1.33
    0010
    -1.33
    going
    -1.32
    minster
    -1.32
     Vanilla
    -1.29
    Cap
    -1.28
    POSITIVE LOGITS
     alike
    1.99
     respectively
    1.68
    itals
    1.48
    encers
    1.42
    GBT
    1.41
    PHOTOS
    1.41
     Snapchat
    1.32
    ORTS
    1.32
    avage
    1.30
    Uber
    1.22
    Activations Density 0.008%

    No Known Activations