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. 9-ATT-KK
    6. 171
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases indicating emotional states or personal perspectives

    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
    0:0.05
    1:0.02
    2:0.06
    3:0.16
    4:0.03
    5:0.03
    6:0.02
    7:0.07
    8:0.03
    9:0.01
    10:0.46
    11:0.02
    Negative Logits
    but
    -2.45
     Annotations
    -2.05
     but
    -2.05
     But
    -1.99
     Carbuncle
    -1.88
    MpServer
    -1.86
    allah
    -1.86
     Temp
    -1.86
    ivery
    -1.83
    ioch
    -1.82
    POSITIVE LOGITS
     nonetheless
    3.57
     seldom
    2.97
     beware
    2.95
     underestimated
    2.92
     instead
    2.91
    instead
    2.86
     hardly
    2.84
     overlooked
    2.81
     underest
    2.77
     never
    2.73
    Activations Density 1.164%

    No Known Activations