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. 11280
    Prev
    Next
    INDEX
    Explanations

    the letter "B" and punctuation marks such as periods and commas

    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
    0:0.07
    1:0.04
    2:0.05
    3:0.03
    4:0.06
    5:0.04
    6:0.23
    7:0.05
    8:0.06
    9:0.23
    10:0.03
    11:0.05
    Negative Logits
     pal
    -3.92
     Palest
    -3.74
     Pal
    -3.72
     skim
    -3.50
    Pal
    -3.37
     PAL
    -3.34
    pal
    -3.32
    pel
    -3.31
    kat
    -3.19
    ocal
    -3.15
    POSITIVE LOGITS
     Dixon
    10.52
    ixon
    5.54
     Dawson
    4.27
    dm
    4.07
     Dong
    3.93
     Dart
    3.86
     Doll
    3.81
     Dud
    3.79
     Rhodes
    3.77
     Hogan
    3.76
    Activations Density 0.001%

    No Known Activations