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. 9-ATT-KK
    6. 20614
    Prev
    Next
    INDEX
    Explanations

    references to rules, penalties, and comments made about player conduct and performance

    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
    0:0.09
    1:0.03
    2:0.04
    3:0.03
    4:0.06
    5:0.02
    6:0.27
    7:0.04
    8:0.07
    9:0.24
    10:0.01
    11:0.03
    Negative Logits
    Indiana
    -4.10
    Parent
    -3.81
     HDR
    -3.75
    XM
    -3.72
     Indiana
    -3.69
     PlayStation
    -3.64
     telev
    -3.58
    Walker
    -3.56
     Playstation
    -3.50
     sprite
    -3.49
    POSITIVE LOGITS
     Ber
    10.92
    Ber
    10.08
     Berger
    7.05
     Berry
    5.45
     ber
    5.32
     Berg
    5.29
     Wer
    4.90
    BER
    4.83
    ber
    4.80
     Borg
    4.76
    Activations Density 0.012%

    No Known Activations