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. 2-ATT-KK
    6. 22395
    Prev
    Next
    INDEX
    Explanations

    organizations, titles, and structured text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to various organizations or entities, particularly in a formal or official context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.08
    3:0.07
    4:0.02
    5:0.15
    6:0.11
    7:0.10
    8:0.04
    9:0.06
    10:0.17
    11:0.09
    Negative Logits
     alike
    -1.08
     lay
    -1.03
     moreover
    -0.95
     loos
    -0.91
     meanwhile
    -0.91
     suff
    -0.90
     crafts
    -0.90
     likewise
    -0.87
     tyres
    -0.87
     undert
    -0.86
    POSITIVE LOGITS
    maxwell
    1.65
    Introdu
    1.24
    Meet
    1.14
    wcsstore
    1.13
    onymous
    1.13
    ptin
    1.10
    GGGGGGGG
    1.09
    ixel
    1.07
    reetings
    1.06
    Bal
    1.05
    Activations Density 0.064%

    No Known Activations