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. 9-ATT-KK
    6. 3051
    Prev
    Next
    INDEX
    Explanations

    instances of navigation or passage between different realms or spaces

    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
    0:0.07
    1:0.02
    2:0.05
    3:0.26
    4:0.04
    5:0.05
    6:0.04
    7:0.10
    8:0.05
    9:0.03
    10:0.21
    11:0.03
    Negative Logits
     Pwr
    -2.20
     padded
    -1.83
     weld
    -1.82
     anchors
    -1.79
     anchored
    -1.75
    USD
    -1.72
    "},
    -1.70
     tripled
    -1.68
     simultane
    -1.67
     curls
    -1.67
    POSITIVE LOGITS
    Contents
    2.26
    bringer
    2.17
    potion
    2.15
    species
    2.12
    ‎
    2.09
    Topic
    2.09
    ヤ
    2.00
    Origin
    1.96
    Synopsis
    1.94
    Appearance
    1.91
    Activations Density 0.001%

    No Known Activations