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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10134
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consequences or results related to events or actions

    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
    2:0.12
    3:0.28
    4:0.02
    5:0.03
    6:0.06
    7:0.12
    8:0.08
    9:0.05
    10:0.06
    11:0.08
    Negative Logits
    Downloadha
    -1.35
     fri
    -1.12
    activated
    -1.07
    bats
    -1.07
    utical
    -1.05
    Jar
    -1.03
    IFE
    -1.00
    pired
    -0.99
     stalk
    -0.98
    TY
    -0.97
    POSITIVE LOGITS
     downstream
    1.25
     subtract
    1.16
     ⓘ
    1.13
     Fowler
    1.09
    abwe
    1.03
    estival
    1.02
    itol
    1.02
    otos
    1.01
     Chinatown
    0.99
     corrid
    0.98
    Activations Density 0.005%

    No Known Activations