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. 27980
    Prev
    Next
    INDEX
    Explanations

    temporal markers and indicators of sequence or timing

    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
    0:0.03
    1:0.03
    2:0.03
    3:0.08
    4:0.40
    5:0.04
    6:0.07
    7:0.09
    8:0.04
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
     contend
    -1.59
     stretching
    -1.42
     ups
    -1.41
     repercussions
    -1.40
     Nanto
    -1.39
     ramifications
    -1.38
     varying
    -1.36
     ticking
    -1.36
     indication
    -1.32
     simulate
    -1.32
    POSITIVE LOGITS
    wei
    1.79
    abase
    1.77
    won
    1.58
    nen
    1.56
    ourcing
    1.55
    psc
    1.55
    phal
    1.50
    pai
    1.50
    ocket
    1.49
     Speedway
    1.48
    Activations Density 0.004%

    No Known Activations