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. 7-ATT-KK
    6. 9431
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only" and its variations, often emphasizing singularity or uniqueness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.05
    2:0.02
    3:0.38
    4:0.06
    5:0.08
    6:0.04
    7:0.02
    8:0.08
    9:0.11
    10:0.01
    11:0.02
    Negative Logits
     secondly
    -2.24
    inally
    -2.02
    bolt
    -1.94
    ationally
    -1.80
     intermedi
    -1.79
    ername
    -1.75
    mere
    -1.72
     intermediate
    -1.71
    cule
    -1.67
    ocre
    -1.66
    POSITIVE LOGITS
    FontSize
    2.29
    ゼウス
    2.25
    Synopsis
    2.15
    SEE
    1.97
     Affect
    1.92
    ================================================================
    1.90
    ATS
    1.87
    aneers
    1.86
     Shades
    1.81
     affected
    1.81
    Activations Density 0.039%

    No Known Activations