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. 9274
    Prev
    Next
    INDEX
    Explanations

    phrases related to government inefficiency and failures

    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
    0:0.03
    1:0.40
    2:0.01
    3:0.06
    4:0.02
    5:0.11
    6:0.09
    7:0.06
    8:0.03
    9:0.06
    10:0.06
    11:0.02
    Negative Logits
     Guests
    -2.93
    scribe
    -2.61
     kisses
    -2.40
     themed
    -2.30
     celebr
    -2.29
     excerpts
    -2.28
    charges
    -2.28
     guests
    -2.26
    Adds
    -2.25
    seys
    -2.24
    POSITIVE LOGITS
     inadequate
    4.26
     incompet
    4.07
     incompetent
    4.01
    adequ
    4.00
     inadequ
    3.80
     incapable
    3.76
     insufficient
    3.73
    failed
    3.72
     inefficient
    3.70
     inability
    3.65
    Activations Density 0.533%

    No Known Activations