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. 7558
    Prev
    Next
    INDEX
    Explanations

    instances of preparation, organization, and the act of presenting or performing in various contexts

    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
    1:0.02
    2:0.05
    3:0.16
    4:0.02
    5:0.07
    6:0.02
    7:0.04
    8:0.02
    9:0.01
    10:0.46
    11:0.02
    Negative Logits
    ⓘ
    -2.50
    chant
    -2.30
    ック
    -2.12
    َ
    -2.08
    angible
    -2.00
    �
    -1.99
     ⓘ
    -1.98
    ِ
    -1.98
    YA
    -1.96
    */(
    -1.96
    POSITIVE LOGITS
     accordingly
    3.04
     beforehand
    2.72
     suitable
    2.55
     carefully
    2.53
     wisely
    2.49
     appropriately
    2.37
     for
    2.32
     meticulously
    2.22
     plan
    2.13
     perfectly
    2.10
    Activations Density 0.267%

    No Known Activations