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. 3086
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or unexpected outcomes

    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
    1:0.02
    2:0.21
    3:0.10
    4:0.03
    5:0.06
    6:0.03
    7:0.06
    8:0.03
    9:0.03
    10:0.15
    11:0.04
    Negative Logits
     transc
    -2.31
     accessibility
    -2.26
     retri
    -2.22
     tag
    -2.19
     commer
    -2.16
     recorder
    -2.09
     conserv
    -2.05
     refere
    -2.03
     access
    -2.00
     accessible
    -1.99
    POSITIVE LOGITS
    essim
    3.18
    icip
    2.81
     expecting
    2.80
     expectation
    2.69
     reassured
    2.69
     apprehens
    2.67
     underest
    2.62
    eyed
    2.59
     expectations
    2.57
     anticipating
    2.57
    Activations Density 0.011%

    No Known Activations