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. 9-ATT-KK
    6. 11263
    Prev
    Next
    INDEX
    Explanations

    concepts related to light, energy, and wave behavior

    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
    0:0.07
    1:0.04
    2:0.06
    3:0.24
    4:0.04
    5:0.09
    6:0.02
    7:0.10
    8:0.03
    9:0.01
    10:0.21
    11:0.03
    Negative Logits
    ploma
    -2.05
     vets
    -2.01
     blogging
    -1.98
     docs
    -1.94
    Education
    -1.91
    Friends
    -1.90
     bombshell
    -1.90
     professionalism
    -1.86
     Explorer
    -1.85
     Serious
    -1.85
    POSITIVE LOGITS
     perpendicular
    3.25
     perpend
    2.88
     vertically
    2.78
     downwards
    2.75
     horizontally
    2.72
     descending
    2.60
     wavelengths
    2.56
     alternating
    2.55
     wavelength
    2.52
     oscill
    2.47
    Activations Density 0.412%

    No Known Activations