© 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. 2-ATT-KK
    11. 22724
    Prev
    Next
    INDEX
    Explanations

    information related to recognition, awards, and achievements of individuals or organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    recognition and acknowledgment of achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.13
    3:0.06
    4:0.31
    5:0.04
    6:0.02
    7:0.02
    8:0.17
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
    wrap
    -1.67
    interrupted
    -1.62
    lite
    -1.52
    wid
    -1.50
    cum
    -1.49
    lette
    -1.47
    loader
    -1.44
    unia
    -1.44
    east
    -1.43
    lus
    -1.43
    POSITIVE LOGITS
     behavi
    1.57
    ��
    1.55
     kindness
    1.48
     Citiz
    1.41
    Merit
    1.39
    ADRA
    1.39
     Presence
    1.37
     unlaw
    1.34
     uniqueness
    1.33
     Computing
    1.33
    Activations Density 0.016%

    No Known Activations