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. 5-ATT-KK
    6. 27668
    Prev
    Next
    INDEX
    Explanations

    terms related to "Rachel" and other variations of the name within contexts discussing reality TV, particularly related to The Bachelor franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.06
    4:0.06
    5:0.04
    6:0.12
    7:0.16
    8:0.04
    9:0.04
    10:0.20
    11:0.13
    Negative Logits
    ーク
    -1.39
    wr
    -1.31
    lag
    -1.31
    iery
    -1.30
     retali
    -1.29
     externalToEVAOnly
    -1.27
    ijn
    -1.26
     Kers
    -1.25
    hooting
    -1.23
     undert
    -1.21
    POSITIVE LOGITS
    ileged
    1.33
     Bachelor
    1.29
    ..."
    1.27
     bachelor
    1.27
     trivia
    1.25
    !",
    1.24
     Centauri
    1.24
    .",
    1.22
    Guest
    1.21
     Torah
    1.19
    Activations Density 0.001%

    No Known Activations