Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22250
    Prev
    Next
    INDEX
    Explanations

    references to technology news and related media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.05
    2:0.22
    3:0.11
    4:0.07
    5:0.06
    6:0.03
    7:0.03
    8:0.05
    9:0.20
    10:0.06
    11:0.03
    Negative Logits
    Downloadha
    -1.34
     stains
    -1.33
     unwanted
    -1.26
     rightful
    -1.25
     weeping
    -1.25
     sob
    -1.22
     streaks
    -1.22
    respective
    -1.21
     undesirable
    -1.20
     undes
    -1.20
    POSITIVE LOGITS
    Lens
    1.55
     Powered
    1.54
     Labs
    1.46
     Pione
    1.32
    iland
    1.27
     Innov
    1.25
     specializing
    1.25
     Ampl
    1.24
    ggles
    1.24
    Engine
    1.24
    Activations Density 0.010%

    No Known Activations