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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14654
    Prev
    Next
    INDEX
    Explanations

    statements or quotes from individuals, particularly those that express feelings or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.12
    2:0.07
    3:0.05
    4:0.04
    5:0.02
    6:0.08
    7:0.10
    8:0.02
    9:0.05
    10:0.16
    11:0.04
    Negative Logits
    Shell
    -3.18
    Delta
    -3.17
    Tank
    -2.96
    scroll
    -2.86
    Snake
    -2.62
     Sar
    -2.60
    �
    -2.58
    aghd
    -2.56
    displayText
    -2.54
     Delta
    -2.53
    POSITIVE LOGITS
     Fel
    9.42
    Fel
    8.40
     fel
    5.64
     Felix
    5.14
     Fidel
    3.85
     Fang
    3.71
     Maur
    3.67
     Ele
    3.58
     Calder
    3.46
     Fant
    3.43
    Activations Density 0.010%

    No Known Activations