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. 3-ATT-KK
    6. 8447
    Prev
    Next
    INDEX
    Explanations

    actions related to creation, construction, and summoning responsibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.05
    2:0.11
    3:0.06
    4:0.01
    5:0.05
    6:0.05
    7:0.08
    8:0.30
    9:0.10
    10:0.05
    11:0.07
    Negative Logits
     Bened
    -1.32
    の�
    -1.25
     Recomm
    -1.16
     Stef
    -1.11
     Serie
    -1.10
    olesterol
    -1.08
    ]),
    -1.08
     Statistical
    -1.08
    markets
    -1.07
    ファ
    -1.06
    POSITIVE LOGITS
    amping
    1.19
    amy
    1.19
     intent
    1.18
     penetrating
    1.15
    intent
    1.15
     tampering
    1.11
     interaction
    1.10
     ingestion
    1.09
    ongo
    1.08
     warfare
    1.06
    Activations Density 0.043%

    No Known Activations