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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22544
    Prev
    Next
    INDEX
    Explanations

    symbols or representations regarding various concepts or movements

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

    symbols associated with resistance, social and political issues, and significant relationships

    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
    0:0.05
    1:0.05
    2:0.09
    3:0.08
    4:0.07
    5:0.11
    6:0.03
    7:0.04
    8:0.09
    9:0.21
    10:0.08
    11:0.03
    Negative Logits
    abase
    -1.37
    ibaba
    -1.29
     careers
    -1.28
    esters
    -1.25
     Mellon
    -1.23
    ertation
    -1.22
    iculty
    -1.22
     NBN
    -1.21
    itent
    -1.20
    enium
    -1.20
    POSITIVE LOGITS
    Latin
    1.44
     insign
    1.40
     symbol
    1.36
    pal
    1.31
     gesture
    1.31
     emblem
    1.30
     UNESCO
    1.28
     bearer
    1.26
    Lat
    1.24
     swast
    1.22
    Activations Density 0.016%

    No Known Activations