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. 11443
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details related to antenna design and setup

    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
    0:0.28
    1:0.02
    2:0.13
    3:0.09
    4:0.03
    5:0.07
    6:0.05
    7:0.05
    8:0.06
    9:0.08
    10:0.04
    11:0.03
    Negative Logits
     volunt
    -3.27
     Pens
    -2.86
     confessions
    -2.80
     Substance
    -2.77
     potion
    -2.69
     whisky
    -2.67
     potions
    -2.62
     Dudley
    -2.56
     Cout
    -2.55
    gie
    -2.54
    POSITIVE LOGITS
     antenna
    7.26
     antennas
    7.11
     transmitter
    4.10
    Radio
    3.97
     radio
    3.89
     radios
    3.82
     transmit
    3.82
     broadcasts
    3.81
     broadcasting
    3.81
     transmitting
    3.79
    Activations Density 0.007%

    No Known Activations