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. 5-ATT-KK
    6. 3057
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    0:0.03
    1:0.01
    2:0.13
    3:0.06
    4:0.08
    5:0.02
    6:0.03
    7:0.39
    8:0.02
    9:0.03
    10:0.09
    11:0.04
    Negative Logits
    izont
    -1.79
    ¶
    -1.61
    borne
    -1.53
    ��
    -1.52
    erity
    -1.50
     Wast
    -1.46
     incurred
    -1.42
     secondly
    -1.38
    :]
    -1.37
     sow
    -1.37
    POSITIVE LOGITS
    eers
    1.58
    cone
    1.54
    rette
    1.49
     lineup
    1.49
     salsa
    1.47
     conference
    1.46
    akura
    1.46
    leigh
    1.45
     puzzle
    1.45
    anguage
    1.45
    Activations Density 0.000%

    No Known Activations