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. 3-ATT-KK
    6. 10546
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or action, especially related to "whipping up" or "moving."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.06
    3:0.17
    4:0.02
    5:0.03
    6:0.05
    7:0.08
    8:0.08
    9:0.24
    10:0.08
    11:0.11
    Negative Logits
    anse
    -1.60
     pione
    -1.55
    soDeliveryDate
    -1.50
    ailability
    -1.35
    anwhile
    -1.31
    uilt
    -1.25
    �
    -1.22
    ItemThumbnailImage
    -1.19
    ould
    -1.18
    ossibility
    -1.17
    POSITIVE LOGITS
     whip
    1.33
     furiously
    1.20
     whipping
    1.17
     whipped
    1.16
     OD
    1.14
     ALP
    1.12
     ****
    1.11
     BBQ
    1.10
     yarn
    1.10
     compliant
    1.08
    Activations Density 0.004%

    No Known Activations