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. 18907
    Prev
    Next
    INDEX
    Explanations

    numerical data related to economic metrics

    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
    0:0.08
    1:0.04
    2:0.00
    3:0.11
    4:0.10
    5:0.08
    6:0.03
    7:0.02
    8:0.38
    9:0.06
    10:0.02
    11:0.01
    Negative Logits
    版
    -1.80
    �
    -1.75
     Friendship
    -1.72
    HER
    -1.71
    ¯¯¯¯¯¯¯¯
    -1.65
    STEM
    -1.64
    �
    -1.57
    wen
    -1.56
    yssey
    -1.56
    iph
    -1.56
    POSITIVE LOGITS
     overest
    2.62
     underest
    2.42
     inflated
    2.36
     undue
    2.29
     disproportion
    2.28
     exaggerated
    2.22
     exagger
    2.19
     excess
    2.08
     variance
    2.06
     excessive
    2.04
    Activations Density 0.022%

    No Known Activations