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. 10101
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures

    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
    1:0.16
    2:0.10
    3:0.03
    4:0.02
    5:0.05
    6:0.09
    7:0.06
    8:0.09
    9:0.08
    10:0.06
    11:0.20
    Negative Logits
    arters
    -1.63
     Patreon
    -1.28
    orable
    -1.24
     ASAP
    -1.21
     Chair
    -1.08
    ��
    -1.04
     Advertisement
    -1.03
     preferably
    -1.03
     Artificial
    -1.02
    arial
    -1.01
    POSITIVE LOGITS
    }}
    1.24
     vanished
    1.23
     perceive
    1.19
    eff
    1.17
    ynt
    1.15
    yll
    1.11
    ois
    1.11
    ect
    1.10
     perceived
    1.10
     perce
    1.09
    Activations Density 0.027%

    No Known Activations