© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 42892
    Prev
    Next
    INDEX
    Explanations

    references to games or competitive activities

    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
    0:0.08
    1:0.04
    2:0.07
    3:0.09
    4:0.08
    5:0.10
    6:0.08
    7:0.07
    8:0.08
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
     Cabinet
    -1.83
     denomination
    -1.69
     handcuffs
    -1.66
     backward
    -1.61
     backwards
    -1.54
     cabinet
    -1.51
     overtime
    -1.49
     equival
    -1.43
    paper
    -1.42
     acknowled
    -1.40
    POSITIVE LOGITS
     ·
    1.97
    zee
    1.80
    voy
    1.72
    @
    1.70
    lde
    1.66
    pes
    1.56
    atl
    1.56
    _>
    1.55
    forum
    1.55
    aton
    1.55
    Activations Density 0.000%

    No Known Activations