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. 9263
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or movement

    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
    0:0.07
    1:0.09
    2:0.11
    3:0.07
    4:0.08
    5:0.07
    6:0.08
    7:0.08
    8:0.07
    9:0.07
    10:0.07
    11:0.09
    Negative Logits
     Pyr
    -2.20
     Tem
    -2.13
     Sum
    -2.05
     Sao
    -2.01
     funer
    -2.01
     Del
    -1.99
     subcontract
    -1.98
     ILCS
    -1.98
    oult
    -1.97
     Grac
    -1.95
    POSITIVE LOGITS
    ajor
    2.53
    ursday
    2.39
    �
    2.30
    laughter
    2.29
    igham
    2.28
    automatic
    2.24
    isodes
    2.23
    arth
    2.18
    bard
    2.16
    aneers
    2.14
    Activations Density 0.000%

    No Known Activations