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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11479
    Prev
    Next
    INDEX
    Explanations

    key terms related to identity and social roles

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.12
    4:0.02
    5:0.07
    6:0.01
    7:0.07
    8:0.02
    9:0.01
    10:0.49
    11:0.04
    Negative Logits
    odan
    -2.02
     VIDEOS
    -1.97
    umbn
    -1.88
    romptu
    -1.87
    PsyNetMessage
    -1.86
    fusc
    -1.85
    Topic
    -1.79
     Decoder
    -1.76
    DragonMagazine
    -1.76
    版
    -1.75
    POSITIVE LOGITS
     but
    2.87
     whereas
    2.83
     meaning
    2.38
     and
    2.35
    %,
    2.32
    but
    2.25
    +,
    2.25
    $,
    2.23
    .),
    2.20
     whose
    2.18
    Activations Density 1.781%

    No Known Activations