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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10602
    Prev
    Next
    INDEX
    Explanations

    references to media and public figures in articles

    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
    0:0.08
    1:0.02
    2:0.03
    3:0.14
    4:0.09
    5:0.06
    6:0.05
    7:0.16
    8:0.10
    9:0.03
    10:0.16
    11:0.03
    Negative Logits
     differe
    -2.37
    orem
    -2.30
     regul
    -2.29
     afterward
    -2.27
     soph
    -2.25
     princ
    -2.23
     STL
    -2.21
     prin
    -2.18
    ":-
    -2.17
     reforms
    -2.15
    POSITIVE LOGITS
    Liverpool
    3.08
     Liverpool
    2.97
     Belfast
    2.87
     Anfield
    2.86
     £
    2.85
     NRL
    2.85
     Trafford
    2.79
    £
    2.60
     whisky
    2.52
     Cardiff
    2.47
    Activations Density 0.004%

    No Known Activations