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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 2792
    Prev
    Next
    INDEX
    Explanations

    instances of the word "refreshing" and similar contextual adjectives that convey a sense of renewal or newness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.07
    4:0.08
    5:0.03
    6:0.06
    7:0.45
    8:0.03
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    ategories
    -1.79
    NetMessage
    -1.69
    覚醒
    -1.66
    oppable
    -1.63
    ohyd
    -1.61
    ailability
    -1.60
    iosyncr
    -1.53
    mercial
    -1.53
    selage
    -1.51
    skirts
    -1.49
    POSITIVE LOGITS
     tone
    1.40
    hee
    1.38
     commenting
    1.35
    shine
    1.33
    apy
    1.33
     econom
    1.32
     commenters
    1.31
     commenter
    1.31
    hi
    1.31
     Coffin
    1.29
    Activations Density 0.001%

    No Known Activations