© 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. 5-ATT-KK
    11. 44161
    Prev
    Next
    INDEX
    Explanations

    terms related to holiday celebrations and events, particularly around Christmas and shopping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.07
    3:0.05
    4:0.06
    5:0.04
    6:0.31
    7:0.05
    8:0.04
    9:0.04
    10:0.13
    11:0.13
    Negative Logits
    enta
    -1.36
     neutrality
    -1.23
    66666666
    -1.18
    unicip
    -1.18
    amiya
    -1.15
    estern
    -1.15
     recomb
    -1.14
     decentral
    -1.11
    lucent
    -1.11
    tsky
    -1.10
    POSITIVE LOGITS
    eve
    1.22
    iren
    1.14
    rences
    1.11
    ivari
    1.07
     Carnival
    1.07
    heat
    1.06
     Record
    1.05
     Catch
    1.05
     celebration
    1.00
     theme
    1.00
    Activations Density 0.013%

    No Known Activations