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. 10269
    Prev
    Next
    INDEX
    Explanations

    instances of surprise or disbelief about societal issues and disparities

    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
    1:0.04
    2:0.08
    3:0.04
    4:0.01
    5:0.05
    6:0.04
    7:0.12
    8:0.06
    9:0.08
    10:0.11
    11:0.30
    Negative Logits
     queue
    -1.14
     accountable
    -1.13
     transmission
    -1.08
     shuttle
    -1.07
    qus
    -1.05
     anymore
    -1.04
     quartz
    -1.03
     functioning
    -1.02
    heid
    -1.01
     pyramid
    -1.01
    POSITIVE LOGITS
    undrum
    1.34
    orney
    1.29
    elvet
    1.20
    Congratulations
    1.18
    landish
    1.16
    Ps
    1.14
    onne
    1.14
    pmwiki
    1.13
    founded
    1.10
    TAIN
    1.09
    Activations Density 0.046%

    No Known Activations