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. 9-ATT-KK
    6. 11359
    Prev
    Next
    INDEX
    Explanations

    individual names, particularly notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.09
    5:0.07
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.07
    11:0.08
    Negative Logits
    IGHTS
    -2.68
     fumes
    -2.58
    */(
    -2.52
    isconsin
    -2.52
     strugg
    -2.41
     sparks
    -2.38
     encount
    -2.36
     firefighter
    -2.30
     warn
    -2.27
     CW
    -2.27
    POSITIVE LOGITS
    rax
    2.80
     Epstein
    2.54
     Pain
    2.50
     DirectX
    2.50
     Zin
    2.42
     Levine
    2.41
    614
    2.39
     Payne
    2.38
    shirts
    2.36
    Roberts
    2.34
    Activations Density 0.000%

    No Known Activations