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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37573
    Prev
    Next
    INDEX
    Explanations

    attributes related to physical and magical abilities in a fantasy context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.06
    3:0.11
    4:0.06
    5:0.06
    6:0.03
    7:0.05
    8:0.05
    9:0.10
    10:0.20
    11:0.17
    Negative Logits
    龍�
    -1.47
    population
    -1.38
     surv
    -1.35
    76561
    -1.30
    inav
    -1.27
    */(
    -1.22
    odox
    -1.21
     unden
    -1.20
    ▬
    -1.20
    mble
    -1.17
    POSITIVE LOGITS
     sockets
    1.17
     melee
    1.11
     Casting
    1.09
    rawdownloadcloneembedreportprint
    1.06
     casting
    1.02
     ranged
    1.02
     socket
    1.01
    .:
    1.00
     Wis
    0.99
     Spell
    0.99
    Activations Density 0.032%

    No Known Activations