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. 44404
    Prev
    Next
    INDEX
    Explanations

    references to entities that have been created or defined

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    2:0.18
    3:0.13
    4:0.13
    5:0.05
    6:0.04
    7:0.03
    8:0.10
    9:0.06
    10:0.11
    11:0.08
    Negative Logits
     Bened
    -1.34
     therap
    -1.21
     Ragnar
    -1.19
     Bj
    -1.18
    Bridge
    -1.18
     Vaugh
    -1.17
    jee
    -1.16
    urances
    -1.15
     Wah
    -1.14
     Revelations
    -1.13
    POSITIVE LOGITS
    typically
    1.67
    ardless
    1.67
    odes
    1.37
    ographically
    1.31
    imum
    1.30
     Typically
    1.29
    ˈ
    1.29
    usually
    1.28
    often
    1.27
    utterstock
    1.26
    Activations Density 0.130%

    No Known Activations