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. 9435
    Prev
    Next
    INDEX
    Explanations

    paths or ways forward in various 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
    0:0.06
    1:0.10
    2:0.12
    3:0.04
    4:0.02
    5:0.03
    6:0.04
    7:0.05
    8:0.04
    9:0.04
    10:0.39
    11:0.03
    Negative Logits
    aii
    -2.43
     Sov
    -2.28
    otin
    -2.22
     iPad
    -2.14
    atur
    -2.01
    �醒
    -2.00
     reserv
    -2.00
     Beau
    -1.97
    inate
    -1.95
     Gins
    -1.93
    POSITIVE LOGITS
    path
    5.07
    Path
    5.00
    PATH
    4.94
     Path
    4.73
     path
    4.34
     PATH
    4.25
     paths
    3.98
     pathway
    3.45
     pathways
    3.07
    Road
    2.48
    Activations Density 0.002%

    No Known Activations