Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44415
    Prev
    Next
    INDEX
    Explanations

    temporal references indicating specific days and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.07
    3:0.16
    4:0.12
    5:0.05
    6:0.07
    7:0.03
    8:0.07
    9:0.12
    10:0.11
    11:0.11
    Negative Logits
     [*]
    -1.35
    ovember
    -1.34
    >]
    -1.30
    undy
    -1.27
     bom
    -1.23
    .</
    -1.21
    -)
    -1.18
    �
    -1.17
    eering
    -1.16
    ————————
    -1.16
    POSITIVE LOGITS
     Column
    1.17
     Uri
    1.15
     Radio
    1.13
    volt
    1.08
     columnist
    1.08
    equal
    1.08
     Koreans
    1.07
     Medline
    1.07
     outfielder
    1.06
     Router
    1.05
    Activations Density 0.053%

    No Known Activations