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. 7-ATT-KK
    6. 9583
    Prev
    Next
    INDEX
    Explanations

    expressions of obligation and expectations in relational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.02
    3:0.06
    4:0.02
    5:0.03
    6:0.02
    7:0.01
    8:0.38
    9:0.31
    10:0.01
    11:0.01
    Negative Logits
     circulation
    -1.92
     Fog
    -1.68
     secondly
    -1.66
     rift
    -1.63
     Lauder
    -1.59
     Chat
    -1.57
     Warm
    -1.56
     Split
    -1.53
     Sovere
    -1.53
     Alloy
    -1.50
    POSITIVE LOGITS
    Filename
    2.07
     entails
    2.06
     instinct
    1.95
     dictated
    1.92
     done
    1.85
     accomplished
    1.83
     practicable
    1.81
     exped
    1.78
    done
    1.77
     pract
    1.77
    Activations Density 0.058%

    No Known Activations