© 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. 35676
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive contributions or advantages within a context

    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
    0:0.02
    1:0.02
    2:0.07
    3:0.09
    4:0.10
    5:0.02
    6:0.03
    7:0.46
    8:0.02
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
    uez
    -1.77
    umblr
    -1.68
    ELS
    -1.59
    Course
    -1.55
    LES
    -1.55
    ONT
    -1.54
    igon
    -1.53
    NetMessage
    -1.47
    adult
    -1.44
    rys
    -1.43
    POSITIVE LOGITS
     ranking
    1.58
     outweigh
    1.55
     Maxim
    1.49
     additions
    1.46
     increases
    1.44
    ighed
    1.44
     Supplement
    1.44
    icient
    1.41
     bonus
    1.41
     Saving
    1.39
    Activations Density 0.001%

    No Known Activations