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. 7734
    Prev
    Next
    INDEX
    Explanations

    statements from various public figures and their opinions on political matters

    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
    0:0.03
    1:0.12
    2:0.06
    3:0.02
    4:0.03
    5:0.06
    6:0.06
    7:0.08
    8:0.14
    9:0.23
    10:0.05
    11:0.09
    Negative Logits
     backdrop
    -1.39
     gram
    -1.27
     vantage
    -1.21
     Gram
    -1.21
     Gry
    -1.19
    DAQ
    -1.15
     hinges
    -1.14
     competition
    -1.09
     bloodstream
    -1.08
    Gall
    -1.07
    POSITIVE LOGITS
    Downloadha
    1.45
     "{
    1.43
     goodbye
    1.39
    psc
    1.37
    amera
    1.30
    omething
    1.30
    kef
    1.29
    anne
    1.27
    :]
    1.22
     "'
    1.21
    Activations Density 0.002%

    No Known Activations