Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11186
    Prev
    Next
    INDEX
    Explanations

    references to extraterrestrial life and their interactions with humans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.25
    1:0.03
    2:0.10
    3:0.10
    4:0.04
    5:0.10
    6:0.04
    7:0.10
    8:0.04
    9:0.03
    10:0.08
    11:0.04
    Negative Logits
     coli
    -2.52
    agate
    -2.36
     microbi
    -2.32
    oked
    -2.18
    bage
    -2.17
     archae
    -2.09
    nsics
    -2.05
    acan
    -2.04
    vine
    -2.03
    eele
    -2.03
    POSITIVE LOGITS
     triangular
    2.52
     hovering
    2.44
     Components
    2.38
    HUD
    2.35
     Compass
    2.26
     constellation
    2.24
     diameter
    2.24
    shape
    2.23
     HUD
    2.21
     rotor
    2.17
    Activations Density 0.001%

    No Known Activations