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. 7-ATT-KK
    6. 9110
    Prev
    Next
    INDEX
    Explanations

    references to legal or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.03
    2:0.02
    3:0.10
    4:0.06
    5:0.10
    6:0.06
    7:0.02
    8:0.11
    9:0.23
    10:0.03
    11:0.02
    Negative Logits
     distances
    -2.21
    antics
    -1.83
     downs
    -1.80
     environmentally
    -1.65
     timeframe
    -1.64
     tackling
    -1.60
     refining
    -1.60
     Downs
    -1.56
     rapes
    -1.56
     feminism
    -1.54
    POSITIVE LOGITS
    quished
    2.06
    hub
    2.03
    Wan
    2.00
    HO
    1.91
    �
    1.85
    scroll
    1.81
    �
    1.80
    edient
    1.77
    KEN
    1.77
    BuyableInstoreAndOnline
    1.76
    Activations Density 0.000%

    No Known Activations