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. 18777
    Prev
    Next
    INDEX
    Explanations

    quantifiers and commands related to actions

    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
    0:0.03
    1:0.07
    2:0.06
    3:0.04
    4:0.02
    5:0.03
    6:0.04
    7:0.04
    8:0.03
    9:0.04
    10:0.51
    11:0.04
    Negative Logits
    anni
    -2.43
    isSpecialOrderable
    -2.29
    ival
    -2.19
    oco
    -2.09
    fml
    -2.00
    API
    -1.99
    iver
    -1.97
     MLG
    -1.92
    arer
    -1.92
     Prol
    -1.91
    POSITIVE LOGITS
    downs
    3.50
    down
    3.26
    Down
    3.22
    DOWN
    3.17
     Down
    3.17
     DOWN
    3.15
     down
    3.14
     downs
    2.88
     Downs
    2.72
     Zub
    2.48
    Activations Density 0.022%

    No Known Activations