Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 7712
    Prev
    Next
    INDEX
    Explanations

    references to people and their actions

    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
    1:0.28
    2:0.09
    3:0.05
    4:0.02
    5:0.03
    6:0.09
    7:0.05
    8:0.02
    9:0.23
    10:0.04
    11:0.01
    Negative Logits
    ondon
    -3.28
    essen
    -2.69
    hon
    -2.67
    genre
    -2.60
     Gon
    -2.58
    1997
    -2.54
    atern
    -2.54
    egal
    -2.52
    lon
    -2.51
     17
    -2.50
    POSITIVE LOGITS
    needed
    6.05
     needed
    6.00
    needs
    5.91
     needs
    5.91
    need
    5.78
     need
    5.73
     Needs
    5.53
     NEED
    5.39
     Need
    5.03
    Need
    4.55
    Activations Density 0.040%

    No Known Activations