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. 9-ATT-KK
    6. 20645
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or important events

    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
    0:0.06
    1:0.23
    2:0.06
    3:0.06
    4:0.04
    5:0.04
    6:0.14
    7:0.02
    8:0.03
    9:0.20
    10:0.04
    11:0.02
    Negative Logits
    vernment
    -3.22
     Disp
    -3.13
     Geh
    -3.11
     Zam
    -2.87
     Wilde
    -2.84
     Walters
    -2.70
     Ward
    -2.70
     Salam
    -2.68
     surfing
    -2.67
     Moe
    -2.67
    POSITIVE LOGITS
    together
    5.14
     Together
    4.70
    Together
    4.58
    comb
    4.54
     together
    4.48
    Comb
    4.46
     combination
    4.37
     combined
    4.18
     Combined
    4.18
     unite
    4.12
    Activations Density 0.001%

    No Known Activations