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. 14037
    Prev
    Next
    INDEX
    Explanations

    phrases and names related to a specific historical site, Fort Ross

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.06
    1:0.03
    2:0.23
    3:0.07
    4:0.22
    5:0.05
    6:0.01
    7:0.02
    8:0.07
    9:0.10
    10:0.04
    11:0.02
    Negative Logits
     Kron
    -1.45
     Categories
    -1.33
     favour
    -1.30
    conom
    -1.26
    origin
    -1.24
    psy
    -1.23
    organic
    -1.20
    м
    -1.18
    hua
    -1.18
    soDeliveryDate
    -1.14
    POSITIVE LOGITS
    aucuses
    1.29
     Hick
    1.22
     checkpoints
    1.19
    Lt
    1.17
    essions
    1.16
    reach
    1.15
     reserve
    1.12
    LOD
    1.12
     Studios
    1.11
     freeway
    1.11
    Activations Density 0.014%

    No Known Activations