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. 3079
    Prev
    Next
    INDEX
    Explanations

    instances of management and decision-making related to systemic issues

    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
    0:0.06
    1:0.03
    2:0.05
    3:0.23
    4:0.04
    5:0.06
    6:0.03
    7:0.08
    8:0.22
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     Caribbean
    -2.41
     contingency
    -2.36
     overlapping
    -2.29
     monop
    -2.23
     Mississ
    -2.23
     Haitian
    -2.21
     Cart
    -2.21
     Tarant
    -2.18
     proxies
    -2.17
     attachments
    -2.16
    POSITIVE LOGITS
    田
    3.79
    ヘ
    3.56
    �
    3.54
    anyahu
    3.44
     �
    3.33
    ラン
    3.24
    ş
    3.17
    ビ
    3.17
    デ
    3.13
    �
    3.08
    Activations Density 0.052%

    No Known Activations