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. 3-ATT-KK
    6. 7867
    Prev
    Next
    INDEX
    Explanations

    mentions of iOS versions and their features or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.04
    2:0.04
    3:0.13
    4:0.03
    5:0.05
    6:0.17
    7:0.21
    8:0.05
    9:0.06
    10:0.09
    11:0.05
    Negative Logits
    yss
    -1.37
    tein
    -1.19
    bil
    -1.14
    arranted
    -1.12
    ocular
    -1.12
    estinal
    -1.10
    avering
    -1.10
    itual
    -1.08
    rosse
    -1.08
    ibling
    -1.07
    POSITIVE LOGITS
    Developer
    1.51
     simulator
    1.29
     Developer
    1.19
    Writer
    1.18
     livest
    1.18
    Bound
    1.14
    ortium
    1.14
     Version
    1.11
     disadvant
    1.11
     Mutant
    1.09
    Activations Density 0.010%

    No Known Activations