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. 44389
    Prev
    Next
    INDEX
    Explanations

    instances of central-themed markers or symbols in a discussion

    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
    1:0.02
    2:0.22
    3:0.06
    4:0.12
    5:0.03
    6:0.10
    7:0.08
    8:0.08
    9:0.05
    10:0.07
    11:0.10
    Negative Logits
     Pist
    -1.44
     AMA
    -1.43
     Planned
    -1.42
     prov
    -1.41
     Apache
    -1.39
     GOT
    -1.39
     Calder
    -1.38
     Ord
    -1.34
    Reloaded
    -1.33
     BLM
    -1.30
    POSITIVE LOGITS
    nesota
    1.81
     neighb
    1.73
    heastern
    1.66
    ayne
    1.62
    itars
    1.58
    uers
    1.58
    tnc
    1.57
    waukee
    1.55
    Downloadha
    1.53
    assetsadobe
    1.50
    Activations Density 0.000%

    No Known Activations