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. 9607
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and institutions, especially in the context of Japan

    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
    0:0.10
    1:0.03
    2:0.01
    3:0.08
    4:0.34
    5:0.09
    6:0.05
    7:0.02
    8:0.09
    9:0.10
    10:0.01
    11:0.02
    Negative Logits
    ��
    -2.82
    ]=
    -2.34
    �
    -2.32
    qus
    -2.29
     srfAttach
    -2.28
    comments
    -2.19
     weren
    -2.19
    }}
    -2.17
    urg
    -2.16
    izont
    -2.11
    POSITIVE LOGITS
     consisting
    2.53
     designed
    2.48
     Pict
    2.37
    quartered
    2.37
     comprising
    2.27
     Located
    2.20
     whose
    2.18
     dating
    2.10
     Designed
    2.09
     featuring
    2.08
    Activations Density 0.322%

    No Known Activations