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. 7844
    Prev
    Next
    INDEX
    Explanations

    actions and their sequences in a narrative context

    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
    0:0.02
    1:0.27
    2:0.07
    3:0.02
    4:0.03
    5:0.09
    6:0.08
    7:0.04
    8:0.08
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
    BuyableInstoreAndOnline
    -1.60
    ajor
    -1.53
    luster
    -1.36
     Leban
    -1.34
     Category
    -1.33
     Posted
    -1.31
    Merit
    -1.28
     Constantin
    -1.27
     Mercedes
    -1.27
     Renault
    -1.24
    POSITIVE LOGITS
    hod
    1.73
     thereafter
    1.56
     accordingly
    1.47
     proceeded
    1.33
     thereof
    1.32
     versa
    1.32
    hol
    1.31
     afterwards
    1.28
    ��
    1.27
    /(
    1.26
    Activations Density 0.201%

    No Known Activations