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. 7371
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific discoveries and research findings

    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
    0:0.07
    1:0.04
    2:0.11
    3:0.12
    4:0.08
    5:0.05
    6:0.09
    7:0.07
    8:0.08
    9:0.06
    10:0.08
    11:0.09
    Negative Logits
    cair
    -1.40
     Curve
    -1.38
    ?)
    -1.34
    ?,
    -1.31
     shack
    -1.30
    pread
    -1.28
    EStream
    -1.28
    Indian
    -1.25
    yip
    -1.19
     Esk
    -1.19
    POSITIVE LOGITS
    entimes
    1.27
    ovember
    1.26
     Courier
    1.25
    quote
    1.24
    translation
    1.24
     lookup
    1.24
     refrain
    1.20
    EO
    1.20
    ometry
    1.19
     ende
    1.18
    Activations Density 0.005%

    No Known Activations