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. 9-ATT-KK
    6. 3170
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" in a context related to quantity or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.08
    2:0.09
    3:0.08
    4:0.06
    5:0.09
    6:0.06
    7:0.07
    8:0.09
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    Israeli
    -2.96
    Friends
    -2.90
    Palestinian
    -2.89
    folios
    -2.85
    Jewish
    -2.81
    ??
    -2.78
    boy
    -2.77
    Ford
    -2.75
    gerald
    -2.73
    Center
    -2.71
    POSITIVE LOGITS
     ozone
    2.86
     sequ
    2.77
     crunch
    2.73
     underwater
    2.73
     tabl
    2.69
     coastline
    2.59
     glac
    2.59
     latency
    2.57
     modulation
    2.57
     understatement
    2.54
    Activations Density 0.000%

    No Known Activations