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. 9247
    Prev
    Next
    INDEX
    Explanations

    phrases related to obligations, rights, and fairness

    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
    0:0.08
    1:0.05
    2:0.02
    3:0.17
    4:0.08
    5:0.13
    6:0.04
    7:0.03
    8:0.10
    9:0.22
    10:0.01
    11:0.01
    Negative Logits
    ipop
    -1.68
     unsus
    -1.59
     streak
    -1.55
     promised
    -1.53
     previous
    -1.52
     hitherto
    -1.50
     promise
    -1.50
     psi
    -1.49
    aline
    -1.48
     splits
    -1.47
    POSITIVE LOGITS
    uters
    2.23
     responsibly
    2.14
    instead
    1.91
    ctuary
    1.82
    ardless
    1.81
    cknow
    1.80
    hern
    1.72
    arna
    1.70
    avoid
    1.69
     ASAP
    1.68
    Activations Density 0.257%

    No Known Activations