© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35824
    Prev
    Next
    INDEX
    Explanations

    instances of interpersonal communication or social interactions

    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
    0:0.06
    1:0.02
    2:0.09
    3:0.17
    4:0.07
    5:0.09
    6:0.02
    7:0.03
    8:0.08
    9:0.13
    10:0.11
    11:0.09
    Negative Logits
    ="#
    -1.38
    20439
    -1.35
    ーク
    -1.28
    ashington
    -1.23
    utterstock
    -1.16
    astical
    -1.12
    arist
    -1.11
     empir
    -1.11
    agonists
    -1.10
     Rousse
    -1.10
    POSITIVE LOGITS
    ..."
    2.60
     …"
    2.56
    ..."
    2.54
    …"
    2.49
    …."
    2.26
    )."
    2.22
     [
    2.04
    .'"
    2.04
     ['
    1.92
    .")
    1.89
    Activations Density 0.452%

    No Known Activations