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. 9-ATT-KK
    6. 7725
    Prev
    Next
    INDEX
    Explanations

    instances of demands or calls for action, particularly relating to government or justice

    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
    0:0.05
    1:0.02
    2:0.08
    3:0.20
    4:0.01
    5:0.08
    6:0.01
    7:0.04
    8:0.02
    9:0.02
    10:0.41
    11:0.01
    Negative Logits
     unlucky
    -2.51
    ortunate
    -2.13
     [|
    -2.12
    vir
    -2.09
     Growing
    -2.01
     Emerging
    -1.99
    growing
    -1.95
    aval
    -1.94
    ilst
    -1.92
    piring
    -1.91
    POSITIVE LOGITS
     apology
    3.67
     refund
    3.33
     restitution
    3.27
     recomp
    3.16
     concessions
    3.10
     refunds
    3.04
     extradition
    3.00
     halt
    2.96
     clarification
    2.94
     redress
    2.94
    Activations Density 0.335%

    No Known Activations