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. 3-ATT-KK
    6. 10297
    Prev
    Next
    INDEX
    Explanations

    references to policies and news articles, particularly in the context of uploads and content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.09
    2:0.24
    3:0.07
    4:0.04
    5:0.05
    6:0.07
    7:0.09
    8:0.09
    9:0.06
    10:0.07
    11:0.05
    Negative Logits
    ichick
    -1.20
    ctor
    -1.06
    hler
    -1.05
     Rosenstein
    -1.05
     Saban
    -1.05
     Sinai
    -1.03
     tack
    -1.03
    ofer
    -1.02
    yip
    -1.02
    itably
    -0.99
    POSITIVE LOGITS
    tnc
    1.45
    /.
    1.29
    /)
    1.24
    /,
    1.21
    /#
    1.14
    ournals
    1.13
    eatured
    1.10
    bb
    1.06
    /"
    1.06
    Month
    1.06
    Activations Density 0.020%

    No Known Activations