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. 10986
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to personal ownership

    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
    3:0.15
    4:0.03
    5:0.05
    6:0.02
    7:0.07
    8:0.03
    9:0.02
    10:0.45
    11:0.03
    Negative Logits
    Reviewer
    -2.74
     nor
    -2.36
    orest
    -2.30
     slightest
    -2.25
    nor
    -2.20
    jar
    -2.14
     Pastebin
    -2.14
    significant
    -2.02
    stad
    -1.98
    most
    -1.98
    POSITIVE LOGITS
    together
    2.66
    aughs
    2.46
     bullshit
    2.36
    achine
    2.34
     together
    2.22
    ê
    2.15
     separately
    2.14
     nonsense
    2.11
     simultaneously
    2.10
     toget
    2.09
    Activations Density 0.125%

    No Known Activations