Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27722
    Prev
    Next
    INDEX
    Explanations

    roles and titles related to leadership or management positions

    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
    0:0.02
    1:0.01
    2:0.10
    3:0.07
    4:0.18
    5:0.03
    6:0.04
    7:0.22
    8:0.03
    9:0.04
    10:0.11
    11:0.10
    Negative Logits
    uries
    -1.65
    aucuses
    -1.62
    OIL
    -1.54
    Background
    -1.51
    コ
    -1.51
    heim
    -1.49
    Winged
    -1.41
    Prof
    -1.39
    assic
    -1.38
    Ear
    -1.36
    POSITIVE LOGITS
     Abedin
    1.52
     PsyNet
    1.50
     Porter
    1.49
     CTR
    1.42
     IMAGES
    1.40
     MSG
    1.38
     ASC
    1.35
     AAC
    1.34
     Huma
    1.34
     McGu
    1.33
    Activations Density 0.022%

    No Known Activations