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. 20655
    Prev
    Next
    INDEX
    Explanations

    references to awards and recognitions related to charitable contributions and social causes

    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
    1:0.03
    2:0.09
    3:0.03
    4:0.05
    5:0.03
    6:0.25
    7:0.04
    8:0.07
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
    cells
    -3.80
     Bradford
    -3.69
     Miliband
    -3.54
    bler
    -3.48
    bb
    -3.47
    ictionary
    -3.45
     Bubble
    -3.42
     sponge
    -3.39
    ipel
    -3.30
    crop
    -3.23
    POSITIVE LOGITS
     Honor
    9.49
    Hon
    7.55
    hon
    7.39
     Hon
    7.06
     honor
    6.44
     dishon
    6.15
     honoring
    5.47
     Honour
    5.31
     honorable
    5.20
     hon
    4.87
    Activations Density 0.003%

    No Known Activations