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. 10-ATT-KK
    6. 14598
    Prev
    Next
    INDEX
    Explanations

    specific sequences of characters or alphanumeric patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.28
    3:0.04
    4:0.05
    5:0.19
    6:0.02
    7:0.05
    8:0.07
    9:0.14
    10:0.03
    11:0.02
    Negative Logits
     pinpoint
    -2.55
     exiled
    -2.52
     stubborn
    -2.48
     devoted
    -2.42
    .�
    -2.42
     prescribed
    -2.42
     painstaking
    -2.42
     Berman
    -2.38
     intuitive
    -2.37
     interchange
    -2.35
    POSITIVE LOGITS
    YC
    4.39
    HQ
    4.27
    FK
    4.25
    Wr
    4.21
    FH
    3.99
    GD
    3.93
    Mp
    3.92
    MN
    3.88
    Gh
    3.82
    UF
    3.82
    Activations Density 0.016%

    No Known Activations