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. 9539
    Prev
    Next
    INDEX
    Explanations

    terms related to academic disciplines and fields of study

    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
    0:0.42
    1:0.02
    2:0.00
    3:0.05
    4:0.06
    5:0.21
    6:0.04
    7:0.02
    8:0.05
    9:0.05
    10:0.01
    11:0.01
    Negative Logits
     raided
    -1.98
     snipers
    -1.87
     typo
    -1.86
     initials
    -1.86
     nicknamed
    -1.85
     disclaimer
    -1.81
     hump
    -1.80
     targets
    -1.80
     billboards
    -1.78
     candles
    -1.76
    POSITIVE LOGITS
    etry
    2.53
    iology
    2.39
    etics
    2.38
    aber
    2.36
    science
    2.34
    ochemistry
    2.31
    iatrics
    2.29
    biology
    2.28
     sciences
    2.26
    rology
    2.23
    Activations Density 0.016%

    No Known Activations