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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27534
    Prev
    Next
    INDEX
    Explanations

    specific nouns and references to names or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.06
    3:0.07
    4:0.10
    5:0.03
    6:0.31
    7:0.03
    8:0.07
    9:0.07
    10:0.08
    11:0.04
    Negative Logits
    quartered
    -2.08
    PLIED
    -1.72
    wcsstore
    -1.61
     horizont
    -1.60
     detrim
    -1.53
    ItemThumbnailImage
    -1.51
     isEnabled
    -1.50
    �
    -1.48
    ailability
    -1.48
     STATS
    -1.45
    POSITIVE LOGITS
    nt
    1.50
    fi
    1.42
    je
    1.38
     bang
    1.37
    uts
    1.33
    yah
    1.33
    nik
    1.31
    ainer
    1.30
     🙂
    1.30
    urst
    1.30
    Activations Density 0.084%

    No Known Activations