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. 5-ATT-KK
    6. 3009
    Prev
    Next
    INDEX
    Explanations

    prepositions and transitional phrases that indicate direction or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.07
    3:0.05
    4:0.14
    5:0.06
    6:0.05
    7:0.31
    8:0.04
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    �
    -2.13
    ivalent
    -1.99
    icrobial
    -1.94
    onyms
    -1.90
    renheit
    -1.80
    �
    -1.80
    agues
    -1.77
    vernment
    -1.69
     [+
    -1.69
    obook
    -1.68
    POSITIVE LOGITS
     undone
    1.75
     resolve
    1.65
     disrupted
    1.65
     Vaughn
    1.62
     sore
    1.61
     shattered
    1.59
     tightened
    1.54
    strings
    1.52
     hamstring
    1.51
     unresolved
    1.47
    Activations Density 0.000%

    No Known Activations