© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28314
    Prev
    Next
    INDEX
    Explanations

    phrases that convey fondness or a strong emotional connection to people, experiences, and memories

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.05
    4:0.08
    5:0.04
    6:0.04
    7:0.39
    8:0.03
    9:0.04
    10:0.08
    11:0.09
    Negative Logits
     predic
    -1.56
    stop
    -1.48
    oppable
    -1.38
    soDeliveryDate
    -1.36
    ciation
    -1.32
    ureau
    -1.30
    eworld
    -1.30
     crises
    -1.27
    vation
    -1.27
     looming
    -1.26
    POSITIVE LOGITS
    76561
    1.56
     dearly
    1.50
     Likes
    1.49
     nostalgic
    1.44
     fond
    1.42
    Used
    1.41
    ィ
    1.40
     mant
    1.39
     nostalg
    1.38
    verty
    1.38
    Activations Density 0.002%

    No Known Activations