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. 2870
    Prev
    Next
    INDEX
    Explanations

    terms related to inquiry, expertise, and action in the context of decision-making and analysis

    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
    0:0.02
    1:0.02
    2:0.23
    3:0.04
    4:0.07
    5:0.04
    6:0.17
    7:0.11
    8:0.02
    9:0.04
    10:0.07
    11:0.09
    Negative Logits
    obal
    -1.65
     sqor
    -1.55
     Falk
    -1.39
     Awakens
    -1.37
     surge
    -1.35
     balloons
    -1.32
     Forth
    -1.29
     Esk
    -1.28
     gravy
    -1.28
     Lancet
    -1.27
    POSITIVE LOGITS
    oyer
    1.64
    tails
    1.62
    :{
    1.61
    ──
    1.53
    三
    1.51
    ISTORY
    1.49
    taboola
    1.48
    thouse
    1.47
    swer
    1.43
    itored
    1.42
    Activations Density 0.008%

    No Known Activations