© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35904
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a sense of belonging or membership within a group

    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
    1:0.02
    2:0.07
    3:0.04
    4:0.13
    5:0.05
    6:0.04
    7:0.11
    8:0.05
    9:0.03
    10:0.12
    11:0.26
    Negative Logits
    pox
    -1.65
    zee
    -1.57
    amy
    -1.55
     Virus
    -1.49
    ruit
    -1.49
    arantine
    -1.48
    iasis
    -1.46
    mary
    -1.45
     Ebola
    -1.43
     Username
    -1.41
    POSITIVE LOGITS
    )=(
    1.72
     ceilings
    1.58
     simultane
    1.56
     designers
    1.51
     resorts
    1.48
     inval
    1.48
     cliffs
    1.45
     contempor
    1.43
     certific
    1.42
     reusable
    1.41
    Activations Density 0.005%

    No Known Activations