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. 8466
    Prev
    Next
    INDEX
    Explanations

    actions related to physical movement or direction

    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
    1:0.03
    2:0.14
    3:0.08
    4:0.02
    5:0.06
    6:0.05
    7:0.09
    8:0.06
    9:0.25
    10:0.10
    11:0.07
    Negative Logits
    catentry
    -1.37
    Enlarge
    -1.35
    Policy
    -1.30
    thood
    -1.19
    グ
    -1.19
     ties
    -1.18
    ドラゴン
    -1.17
     nutshell
    -1.16
    Few
    -1.14
     affinity
    -1.13
    POSITIVE LOGITS
    utters
    1.32
     unnoticed
    1.27
     undet
    1.26
    opian
    1.23
    ridges
    1.22
     Parsons
    1.22
    utter
    1.21
    �
    1.19
     inspecting
    1.17
     inco
    1.17
    Activations Density 0.038%

    No Known Activations