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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27971
    Prev
    Next
    INDEX
    Explanations

    phrases related to opposition or competition

    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
    2:0.08
    3:0.07
    4:0.28
    5:0.02
    6:0.04
    7:0.26
    8:0.02
    9:0.03
    10:0.05
    11:0.07
    Negative Logits
    waters
    -1.52
     Removed
    -1.44
    iano
    -1.44
    ended
    -1.43
    arts
    -1.41
    short
    -1.41
    jar
    -1.40
     guiActiveUnfocused
    -1.39
    advertising
    -1.38
    displayText
    -1.35
    POSITIVE LOGITS
     unbeliev
    1.82
    isSpecialOrderable
    1.73
     behavi
    1.73
     expectations
    1.73
     pros
    1.67
     towering
    1.63
     firepower
    1.60
     temptation
    1.60
     misconceptions
    1.60
     Sph
    1.54
    Activations Density 0.001%

    No Known Activations