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. 10508
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "just."

    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
    0:0.06
    1:0.03
    2:0.13
    3:0.05
    4:0.02
    5:0.05
    6:0.09
    7:0.06
    8:0.13
    9:0.09
    10:0.09
    11:0.14
    Negative Logits
     commence
    -1.13
     consequ
    -1.09
     consult
    -0.99
    clusions
    -0.97
     achieving
    -0.96
    minent
    -0.95
     impart
    -0.94
     exhibiting
    -0.92
     procure
    -0.92
     viability
    -0.91
    POSITIVE LOGITS
     guiActiveUn
    1.37
     Huck
    1.16
     darn
    1.13
    Crystal
    1.10
    NetMessage
    1.06
    龍喚士
    1.04
     gotta
    1.04
    ��
    1.03
     looph
    0.96
     landsl
    0.94
    Activations Density 0.021%

    No Known Activations