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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2838
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize totality or completeness

    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
    1:0.01
    2:0.07
    3:0.06
    4:0.26
    5:0.03
    6:0.25
    7:0.09
    8:0.03
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
     accurately
    -1.57
     ®
    -1.41
     underest
    -1.39
     attributed
    -1.35
     describing
    -1.31
     underestimate
    -1.31
    ori
    -1.31
    rification
    -1.30
     contained
    -1.29
     exhibited
    -1.28
    POSITIVE LOGITS
     realms
    1.78
    stanbul
    1.70
    abad
    1.63
    perate
    1.60
     stages
    1.55
     Balkans
    1.52
    outheastern
    1.52
     depths
    1.52
    gro
    1.46
    Balt
    1.45
    Activations Density 0.000%

    No Known Activations