Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 44283
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports stories and major events in football

    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
    0:0.02
    1:0.02
    2:0.18
    3:0.14
    4:0.15
    5:0.04
    6:0.06
    7:0.11
    8:0.04
    9:0.07
    10:0.06
    11:0.07
    Negative Logits
    livious
    -2.00
    gged
    -1.79
    eder
    -1.63
    ilar
    -1.55
     misinterpret
    -1.52
    aternal
    -1.36
    cific
    -1.36
    nown
    -1.33
    leck
    -1.33
     mism
    -1.31
    POSITIVE LOGITS
     anywhere
    1.52
     TODAY
    1.51
     roundup
    1.50
     LIVE
    1.47
     FREE
    1.41
    Adds
    1.35
     Featured
    1.32
     capability
    1.32
    SN
    1.31
     Explore
    1.29
    Activations Density 0.003%

    No Known Activations