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. 9-ATT-KK
    6. 150
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time duration or future projections

    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
    0:0.03
    1:0.18
    2:0.03
    3:0.07
    4:0.02
    5:0.08
    6:0.03
    7:0.05
    8:0.02
    9:0.03
    10:0.38
    11:0.03
    Negative Logits
    terday
    -2.46
    nesday
    -2.45
    Tuesday
    -2.35
    uria
    -2.25
    Monday
    -2.25
     Tues
    -2.24
    Franc
    -2.20
    October
    -2.13
    uesday
    -2.13
     fres
    -2.09
    POSITIVE LOGITS
    shore
    2.38
    ))))
    2.23
    minecraft
    2.22
     unexpl
    2.22
     unchecked
    2.17
     unanswered
    2.16
     awaited
    2.15
    iper
    2.13
     �
    2.12
    )|
    2.10
    Activations Density 0.004%

    No Known Activations