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. 18708
    Prev
    Next
    INDEX
    Explanations

    instances of media bias and how various entities are portrayed in coverage

    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
    0:0.12
    1:0.01
    2:0.10
    3:0.14
    4:0.02
    5:0.36
    6:0.02
    7:0.05
    8:0.04
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
    Tumblr
    -2.83
     Sync
    -2.39
     Codec
    -2.37
    Writer
    -2.37
    UTC
    -2.36
    Lex
    -2.35
    GMT
    -2.34
     Paste
    -2.32
    pload
    -2.31
    Lic
    -2.28
    POSITIVE LOGITS
     crises
    2.46
     crisis
    2.38
     details
    2.35
     emergencies
    2.33
     Hussein
    2.28
     Mohammed
    2.19
     facts
    2.15
     arrests
    2.13
     massacres
    2.11
     erupt
    2.11
    Activations Density 0.750%

    No Known Activations