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. 20678
    Prev
    Next
    INDEX
    Explanations

    references to technology and communication systems

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.10
    4:0.02
    5:0.04
    6:0.02
    7:0.08
    8:0.02
    9:0.01
    10:0.51
    11:0.06
    Negative Logits
    BuyableInstoreAndOnline
    -1.74
    abel
    -1.56
    nered
    -1.54
     nor
    -1.47
    tackle
    -1.44
    ゼウス
    -1.39
    ],
    -1.35
    stood
    -1.35
    ngth
    -1.33
     ],
    -1.33
    POSITIVE LOGITS
     accordingly
    3.08
     whenever
    2.66
     thereafter
    2.29
    .</
    2.18
    .''.
    2.13
     attRot
    2.11
     afterwards
    2.00
    .�
    2.00
    .?
    1.93
     afterward
    1.92
    Activations Density 1.139%

    No Known Activations