Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18961
    Prev
    Next
    INDEX
    Explanations

    topics related to media analysis and critique, particularly focusing on failures and successes in film and cultural representations

    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
    0:0.06
    1:0.03
    2:0.02
    3:0.10
    4:0.41
    5:0.05
    6:0.04
    7:0.02
    8:0.07
    9:0.13
    10:0.01
    11:0.01
    Negative Logits
    endi
    -2.52
    lycer
    -2.20
    aldo
    -2.08
    icken
    -1.98
    rists
    -1.97
    rafted
    -1.97
    uddin
    -1.91
    alde
    -1.90
    legates
    -1.90
    andy
    -1.89
    POSITIVE LOGITS
    MAP
    2.33
     versus
    2.30
     including
    2.14
     timelines
    2.04
     pitfalls
    2.02
    romeda
    1.97
     detailing
    1.95
     misconceptions
    1.94
    piring
    1.90
     Spoiler
    1.90
    Activations Density 0.684%

    No Known Activations