© 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. 9-ATT-KK
    6. 20733
    Prev
    Next
    INDEX
    Explanations

    references to days of the week, particularly focusing on trends related to suicides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.26
    2:0.03
    3:0.12
    4:0.08
    5:0.10
    6:0.02
    7:0.09
    8:0.03
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
    nesota
    -2.44
    vec
    -2.42
    culus
    -2.31
    abwe
    -2.27
    oming
    -2.06
     deton
    -2.02
     dehydration
    -2.00
    bole
    -1.97
    lyak
    -1.95
     ultraviolet
    -1.95
    POSITIVE LOGITS
     Fridays
    3.35
     Saturdays
    2.89
     whenever
    2.83
    pmwiki
    2.82
    aturdays
    2.72
     Occasionally
    2.71
    Whenever
    2.70
     ALWAYS
    2.66
     CTR
    2.65
    Sometimes
    2.63
    Activations Density 0.005%

    No Known Activations