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. 14701
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly those related to locations and people, as well as mentions of specific events or dates

    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
    0:0.06
    1:0.49
    2:0.05
    3:0.03
    4:0.05
    5:0.02
    6:0.04
    7:0.06
    8:0.02
    9:0.02
    10:0.07
    11:0.04
    Negative Logits
    ロ
    -2.67
    rax
    -2.49
    Interstitial
    -2.43
    END
    -2.41
    GEN
    -2.40
    ajo
    -2.40
    iverse
    -2.38
    aired
    -2.38
    aido
    -2.36
    Winged
    -2.36
    POSITIVE LOGITS
     Hard
    8.99
    Hard
    8.58
    hard
    7.97
     hard
    7.63
     Soft
    6.38
     soft
    6.24
     harder
    6.22
    Soft
    5.86
     hardness
    5.68
    soft
    5.52
    Activations Density 0.132%

    No Known Activations