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. 7-ATT-KK
    6. 18940
    Prev
    Next
    INDEX
    Explanations

    proper nouns and significant names related to political events and organizations

    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
    0:0.13
    1:0.01
    2:0.00
    3:0.10
    4:0.29
    5:0.03
    6:0.02
    7:0.00
    8:0.31
    9:0.04
    10:0.00
    11:0.01
    Negative Logits
     against
    -1.98
    >>>
    -1.94
     hanged
    -1.92
    against
    -1.91
    phal
    -1.88
    elight
    -1.87
     defeated
    -1.80
     ventured
    -1.76
    Ranked
    -1.76
    frey
    -1.74
    POSITIVE LOGITS
     adjustments
    2.02
    ��
    1.74
     editorial
    1.73
     adjustment
    1.72
    depending
    1.67
     reflections
    1.65
     apologies
    1.65
     stabilization
    1.64
     suspensions
    1.61
    ット
    1.60
    Activations Density 0.022%

    No Known Activations