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. 11423
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory entities and classifications

    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
    0:0.09
    1:0.02
    2:0.06
    3:0.22
    4:0.03
    5:0.08
    6:0.02
    7:0.05
    8:0.03
    9:0.02
    10:0.31
    11:0.02
    Negative Logits
     brute
    -2.64
    rived
    -2.29
     trick
    -2.09
    hide
    -2.09
     confuse
    -2.08
     fools
    -2.06
     stunts
    -2.03
    hetto
    -2.02
     tedious
    -2.02
     revel
    -2.02
    POSITIVE LOGITS
    ‎
    2.34
     listed
    2.21
    natureconservancy
    2.15
    DAQ
    2.09
     STATS
    2.08
     ISBN
    1.99
     Autism
    1.95
     PID
    1.95
     Forestry
    1.95
     000
    1.95
    Activations Density 0.014%

    No Known Activations