© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14490
    Prev
    Next
    INDEX
    Explanations

    phrases related to manipulation and interaction with objects in various environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.04
    2:0.04
    3:0.05
    4:0.13
    5:0.04
    6:0.04
    7:0.08
    8:0.02
    9:0.09
    10:0.03
    11:0.31
    Negative Logits
     Crusade
    -2.44
     amnesty
    -2.42
     crackdown
    -2.40
     repentance
    -2.39
    akedown
    -2.38
    breeding
    -2.27
    rition
    -2.26
    otide
    -2.23
    DragonMagazine
    -2.19
    staking
    -2.17
    POSITIVE LOGITS
     objects
    5.70
     Objects
    4.82
    objects
    4.72
     object
    4.00
     stimuli
    3.83
     surfaces
    3.77
    animate
    3.51
     projectiles
    3.44
     particles
    3.38
    object
    3.36
    Activations Density 0.327%

    No Known Activations