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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19170
    Prev
    Next
    INDEX
    Explanations

    locations and places where events or actions occur

    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
    0:0.03
    1:0.01
    2:0.10
    3:0.08
    4:0.29
    5:0.02
    6:0.06
    7:0.16
    8:0.05
    9:0.03
    10:0.06
    11:0.07
    Negative Logits
     accompl
    -1.57
    ratulations
    -1.57
     belie
    -1.48
    advertising
    -1.39
     dstg
    -1.37
     leveraging
    -1.35
     charm
    -1.35
     oneself
    -1.32
     accumulated
    -1.31
     Koreans
    -1.30
    POSITIVE LOGITS
    ricular
    1.35
    Si
    1.33
     Plaza
    1.30
    area
    1.30
    QB
    1.26
     Slip
    1.25
    Sac
    1.24
     Breakfast
    1.23
    aus
    1.22
    iatus
    1.20
    Activations Density 0.003%

    No Known Activations