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. 3-ATT-KK
    6. 8540
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives that modify the intensity or quality of actions and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.05
    2:0.11
    3:0.06
    4:0.02
    5:0.03
    6:0.27
    7:0.05
    8:0.09
    9:0.03
    10:0.08
    11:0.13
    Negative Logits
     Legacy
    -1.03
     Yard
    -0.97
     Appropri
    -0.96
     Spr
    -0.90
     Allow
    -0.87
     Zone
    -0.86
    psey
    -0.86
     optionally
    -0.85
     Legend
    -0.85
     Loft
    -0.85
    POSITIVE LOGITS
    OSP
    1.01
    azor
    1.01
    �
    0.98
    sounding
    0.97
    ��
    0.94
    ubes
    0.93
    oths
    0.93
    �
    0.92
    interstitial
    0.92
    eks
    0.91
    Activations Density 0.021%

    No Known Activations