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. 8417
    Prev
    Next
    INDEX
    Explanations

    aspects related to governance and public policy issues

    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
    0:0.05
    1:0.04
    2:0.09
    3:0.05
    4:0.06
    5:0.09
    6:0.15
    7:0.14
    8:0.06
    9:0.03
    10:0.11
    11:0.07
    Negative Logits
    ega
    -1.36
    amera
    -1.19
    oodle
    -1.16
    oots
    -1.12
     ribbon
    -1.10
     Beg
    -1.08
     Wind
    -1.05
     plush
    -1.04
     troop
    -1.03
     Heal
    -1.03
    POSITIVE LOGITS
    */(
    1.53
     overest
    1.33
    NetMessage
    1.30
    ウス
    1.29
     underest
    1.28
    ◼
    1.26
     outweigh
    1.24
     underestimate
    1.21
    Reviewer
    1.20
     misconceptions
    1.19
    Activations Density 0.426%

    No Known Activations