Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13710
    Prev
    Next
    INDEX
    Explanations

    words related to swearing or making promises

    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
    1:0.04
    2:0.11
    3:0.10
    4:0.13
    5:0.05
    6:0.03
    7:0.04
    8:0.15
    9:0.14
    10:0.06
    11:0.03
    Negative Logits
    Thumbnail
    -1.27
    angular
    -1.14
    NW
    -1.09
    address
    -1.07
    ource
    -1.06
     weigh
    -1.05
    plan
    -1.05
    Solution
    -1.04
     Pond
    -1.03
    oute
    -1.03
    POSITIVE LOGITS
     innocence
    1.32
     supernatural
    1.22
     Hik
    1.18
     loyalty
    1.18
     torture
    1.16
     swear
    1.15
     immortality
    1.14
     Cthulhu
    1.13
     never
    1.12
     princess
    1.12
    Activations Density 0.003%

    No Known Activations