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. 7896
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a significant quantity or degree of something

    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
    0:0.02
    1:0.03
    2:0.09
    3:0.09
    4:0.02
    5:0.03
    6:0.24
    7:0.08
    8:0.06
    9:0.04
    10:0.08
    11:0.16
    Negative Logits
    nell
    -1.13
    pg
    -1.13
     PID
    -1.12
    hester
    -1.12
    eeds
    -1.11
    ello
    -1.09
     SIG
    -1.08
     GEAR
    -1.04
    adelphia
    -1.02
    hner
    -1.02
    POSITIVE LOGITS
    heartedly
    1.02
     antioxidant
    0.95
     Kiw
    0.95
    zbek
    0.94
     Filipino
    0.93
    risome
    0.92
     Finnish
    0.92
     debunked
    0.92
    healthy
    0.91
     Harding
    0.91
    Activations Density 0.012%

    No Known Activations