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. 18784
    Prev
    Next
    INDEX
    Explanations

    dates and chronological references

    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
    0:0.23
    1:0.01
    2:0.05
    3:0.09
    4:0.03
    5:0.07
    6:0.02
    7:0.20
    8:0.06
    9:0.02
    10:0.12
    11:0.04
    Negative Logits
     oun
    -2.22
     answ
    -2.07
     chap
    -2.03
     Detective
    -1.95
    kj
    -1.94
     Pyramid
    -1.93
     Pathfinder
    -1.89
    anooga
    -1.87
     quiz
    -1.83
    handed
    -1.82
    POSITIVE LOGITS
    ridor
    2.06
     EVENT
    2.04
     (/
    2.00
     hasht
    1.99
    tern
    1.97
    llular
    1.93
    REAM
    1.92
    width
    1.91
     (@
    1.90
    iphate
    1.89
    Activations Density 0.012%

    No Known Activations