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. 10706
    Prev
    Next
    INDEX
    Explanations

    phrases that express support or endorsement for various ideas or groups

    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
    0:0.01
    1:0.02
    2:0.08
    3:0.23
    4:0.02
    5:0.02
    6:0.03
    7:0.09
    8:0.06
    9:0.20
    10:0.10
    11:0.08
    Negative Logits
    iture
    -1.44
    odder
    -1.25
    ivation
    -1.23
    ivated
    -1.22
    ipl
    -1.21
    stery
    -1.20
     ILCS
    -1.20
    ulhu
    -1.19
    kes
    -1.18
    gey
    -1.17
    POSITIVE LOGITS
     feminine
    1.13
     CoC
    1.13
     stren
    1.09
     disabled
    1.08
     moderate
    1.06
     degrading
    1.06
     hostile
    1.05
     patriarchal
    1.05
     constructive
    1.05
     whatsoever
    1.04
    Activations Density 0.017%

    No Known Activations