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. 3-ATT-KK
    6. 9993
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and actions related to rights or claims

    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
    0:0.04
    1:0.03
    2:0.05
    3:0.35
    4:0.03
    5:0.03
    6:0.05
    7:0.08
    8:0.03
    9:0.14
    10:0.06
    11:0.07
    Negative Logits
    las
    -1.22
     Winners
    -1.18
    ellen
    -1.16
    friends
    -1.15
    igl
    -1.14
     Gou
    -1.13
     Sensor
    -1.13
    bed
    -1.10
    fort
    -1.04
    0200
    -1.04
    POSITIVE LOGITS
    pta
    1.39
     constitu
    1.39
    riber
    1.30
    tarian
    1.19
    rency
    1.17
     Keeper
    1.16
     ascend
    1.15
     incub
    1.13
     vetting
    1.13
    ometric
    1.12
    Activations Density 0.002%

    No Known Activations