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. 5-ATT-KK
    6. 19210
    Prev
    Next
    INDEX
    Explanations

    mentions of significant social dynamics and public reactions

    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
    1:0.03
    2:0.10
    3:0.12
    4:0.35
    5:0.02
    6:0.06
    7:0.10
    8:0.03
    9:0.02
    10:0.04
    11:0.06
    Negative Logits
     Pwr
    -1.78
    athered
    -1.73
    hern
    -1.72
    etheless
    -1.68
    ranging
    -1.65
    achable
    -1.57
    withstanding
    -1.53
    eatures
    -1.49
    intensive
    -1.48
     municip
    -1.45
    POSITIVE LOGITS
     REALLY
    1.51
     Cookie
    1.46
     thinks
    1.46
     fuss
    1.44
     unfolds
    1.44
     happened
    1.43
     someday
    1.43
     sucks
    1.42
    atech
    1.36
     reminds
    1.35
    Activations Density 0.075%

    No Known Activations