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. 10503
    Prev
    Next
    INDEX
    Explanations

    phrases indicating departure or withdrawal from situations or negotiations

    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
    1:0.03
    2:0.09
    3:0.19
    4:0.02
    5:0.04
    6:0.07
    7:0.10
    8:0.08
    9:0.16
    10:0.05
    11:0.12
    Negative Logits
    PDATE
    -1.43
     anecd
    -1.41
    ufact
    -1.28
    ETF
    -1.27
    TL
    -1.26
    izable
    -1.21
     toget
    -1.20
    >)
    -1.18
    ▬
    -1.16
    =-=-=-=-=-=-=-=-
    -1.16
    POSITIVE LOGITS
    arson
    1.31
     Blues
    1.22
     curfew
    1.13
    ocracy
    0.98
     Auditor
    0.98
    zos
    0.95
     Rahul
    0.95
     McCartney
    0.94
     Chaser
    0.93
     Burke
    0.93
    Activations Density 0.002%

    No Known Activations