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. 18768
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and self-reflection

    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
    0:0.05
    1:0.05
    2:0.06
    3:0.11
    4:0.03
    5:0.05
    6:0.03
    7:0.24
    8:0.04
    9:0.02
    10:0.24
    11:0.03
    Negative Logits
    escription
    -2.43
    ergy
    -2.38
    rafted
    -2.34
     withd
    -2.29
    ociated
    -2.27
    rompt
    -2.27
    cellaneous
    -2.25
    ibus
    -2.23
     separately
    -2.21
     explor
    -2.19
    POSITIVE LOGITS
     ALWAYS
    3.71
     invariably
    3.00
     always
    2.87
    always
    2.77
     forever
    2.76
     wont
    2.62
     NEVER
    2.52
     anytime
    2.48
     inevitably
    2.47
     everywhere
    2.39
    Activations Density 0.017%

    No Known Activations