Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19327
    Prev
    Next
    INDEX
    Explanations

    references to education and institutional announcements

    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
    0:0.12
    1:0.27
    2:0.03
    3:0.03
    4:0.02
    5:0.16
    6:0.03
    7:0.01
    8:0.16
    9:0.06
    10:0.03
    11:0.01
    Negative Logits
     MU
    -1.61
     scoff
    -1.61
     insanity
    -1.56
     socialist
    -1.56
     Tol
    -1.54
     stuffing
    -1.54
     Mania
    -1.53
     faked
    -1.51
     Tant
    -1.50
     socialists
    -1.49
    POSITIVE LOGITS
    �
    2.37
    gae
    2.05
    aughters
    2.00
    ruit
    1.99
    itud
    1.95
    elaide
    1.93
    ��
    1.92
    �醒
    1.92
    abeth
    1.90
    ername
    1.89
    Activations Density 0.028%

    No Known Activations