Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7770
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing simplicity and ease of use

    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
    0:0.01
    1:0.02
    2:0.06
    3:0.32
    4:0.02
    5:0.02
    6:0.05
    7:0.14
    8:0.02
    9:0.02
    10:0.05
    11:0.20
    Negative Logits
    EMENT
    -1.32
    apor
    -1.31
    EStream
    -1.30
    urga
    -1.23
    ONSORED
    -1.22
     Starr
    -1.19
     alt
    -1.19
    alos
    -1.18
     Cheong
    -1.14
    afety
    -1.13
    POSITIVE LOGITS
     Procedure
    1.16
     charm
    1.12
     (<
    1.11
     gritty
    1.10
    {\
    1.09
    otide
    1.09
    glers
    1.09
     Telephone
    1.08
    actionDate
    1.08
    Detroit
    1.07
    Activations Density 0.009%

    No Known Activations