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. 10132
    Prev
    Next
    INDEX
    Explanations

    time indicators and numerical details related to events

    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
    1:0.03
    2:0.11
    3:0.05
    4:0.02
    5:0.04
    6:0.09
    7:0.04
    8:0.04
    9:0.32
    10:0.05
    11:0.14
    Negative Logits
     voices
    -1.27
    ismo
    -1.27
     candid
    -1.26
    onen
    -1.24
    ari
    -1.22
    geon
    -1.22
     NI
    -1.18
    continue
    -1.17
     lanes
    -1.15
    aker
    -1.15
    POSITIVE LOGITS
    anwhile
    1.72
    uble
    1.63
    quartered
    1.41
    init
    1.35
     Wrap
    1.35
    NetMessage
    1.35
    terday
    1.32
    noon
    1.30
    覚醒
    1.30
     srfAttach
    1.29
    Activations Density 0.075%

    No Known Activations