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. 13875
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives to express qualities of people or seasons

    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
    0:0.13
    1:0.04
    2:0.13
    3:0.11
    4:0.13
    5:0.07
    6:0.04
    7:0.03
    8:0.10
    9:0.08
    10:0.06
    11:0.03
    Negative Logits
    ���
    -1.88
    ospace
    -1.60
     councill
    -1.59
    ntil
    -1.56
    eton
    -1.56
     columns
    -1.33
    anooga
    -1.33
     insurers
    -1.26
     expiration
    -1.25
     foregoing
    -1.25
    POSITIVE LOGITS
    liest
    1.67
    cellent
    1.42
     badass
    1.39
     tease
    1.38
    lier
    1.38
    idious
    1.37
     prett
    1.37
     kinda
    1.36
    twitch
    1.35
     teasing
    1.34
    Activations Density 0.003%

    No Known Activations