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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18990
    Prev
    Next
    INDEX
    Explanations

    the word 'go' as a key action or directive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.07
    4:0.06
    5:0.08
    6:0.07
    7:0.08
    8:0.08
    9:0.09
    10:0.09
    11:0.08
    Negative Logits
    iform
    -2.28
    gallery
    -2.19
     narrator
    -2.05
    wav
    -2.04
    reau
    -2.03
     telev
    -1.98
    raphics
    -1.97
     insign
    -1.92
    wings
    -1.92
    arer
    -1.92
    POSITIVE LOGITS
     Niet
    2.92
    グ
    2.29
    \\\\
    2.11
    ドラ
    2.10
    ク
    2.10
    milo
    2.09
     =================
    2.06
    ć
    2.05
     Maced
    2.03
    в
    2.00
    Activations Density 0.000%

    No Known Activations