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. 60
    Prev
    Next
    INDEX
    Explanations

    references to medical recommendations and the consequences of missed care or appointments

    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
    0:0.19
    1:0.03
    2:0.22
    3:0.08
    4:0.03
    5:0.09
    6:0.04
    7:0.05
    8:0.03
    9:0.10
    10:0.04
    11:0.04
    Negative Logits
     shed
    -2.87
     visc
    -2.70
     sweats
    -2.64
     resilience
    -2.48
     Browne
    -2.47
     hoard
    -2.45
     metabol
    -2.40
     FSA
    -2.35
     dump
    -2.34
     losses
    -2.31
    POSITIVE LOGITS
     appointments
    5.06
     appointment
    4.51
    ointment
    3.52
    oplan
    2.87
    phthal
    2.63
     Ascend
    2.61
     appointed
    2.56
    oint
    2.56
     appointing
    2.55
    args
    2.52
    Activations Density 0.001%

    No Known Activations