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. 7-ATT-KK
    6. 9071
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performance metrics

    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
    0:0.09
    1:0.09
    2:0.17
    3:0.06
    4:0.02
    5:0.04
    6:0.06
    7:0.13
    8:0.04
    9:0.03
    10:0.06
    11:0.15
    Negative Logits
    soDeliveryDate
    -2.58
    theless
    -2.18
     DRAG
    -1.88
     Runs
    -1.87
    osponsors
    -1.82
     infiltr
    -1.81
    etheless
    -1.81
     Pavilion
    -1.79
     TP
    -1.78
     themed
    -1.77
    POSITIVE LOGITS
    .;
    2.09
    ophy
    2.05
    wig
    2.00
     Divinity
    1.98
    ament
    1.94
     Webb
    1.92
    ener
    1.90
    resp
    1.89
    agne
    1.88
    growth
    1.84
    Activations Density 0.001%

    No Known Activations