© 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. 22694
    Prev
    Next
    INDEX
    Explanations

    descriptions of people and events

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

    descriptive adjectives and nouns related to performance and artistic expressions

    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
    0:0.07
    1:0.03
    2:0.09
    3:0.16
    4:0.04
    5:0.15
    6:0.04
    7:0.04
    8:0.18
    9:0.05
    10:0.07
    11:0.04
    Negative Logits
    ��
    -1.38
     Sites
    -1.38
    lees
    -1.37
    assies
    -1.33
    mails
    -1.33
    Companies
    -1.28
    ']
    -1.27
    allery
    -1.27
    sites
    -1.27
     Posts
    -1.24
    POSITIVE LOGITS
     twist
    1.77
     flourish
    1.43
     assortment
    1.38
     sample
    1.38
     refill
    1.35
     diagnosis
    1.33
     variety
    1.33
     sunscreen
    1.32
     primer
    1.32
     standpoint
    1.31
    Activations Density 0.174%

    No Known Activations