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. 5-ATT-KK
    6. 7068
    Prev
    Next
    INDEX
    Explanations

    words expressing attitudes or positions regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.07
    3:0.05
    4:0.07
    5:0.03
    6:0.04
    7:0.18
    8:0.05
    9:0.05
    10:0.07
    11:0.30
    Negative Logits
    oji
    -1.91
    femin
    -1.88
     Mothers
    -1.88
     mund
    -1.85
     Femin
    -1.82
    onomy
    -1.79
    oration
    -1.76
    mast
    -1.73
    eme
    -1.73
     Fathers
    -1.69
    POSITIVE LOGITS
    ILLE
    1.94
    entanyl
    1.80
    arrett
    1.70
     lethal
    1.69
     backups
    1.67
    setup
    1.63
     unsus
    1.63
     backup
    1.62
    quickShipAvailable
    1.60
    LP
    1.59
    Activations Density 0.001%

    No Known Activations