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. 3-ATT-KK
    6. 10400
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions and emotional responses

    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
    0:0.05
    1:0.05
    2:0.04
    3:0.02
    4:0.04
    5:0.40
    6:0.06
    7:0.03
    8:0.04
    9:0.04
    10:0.09
    11:0.09
    Negative Logits
    successful
    -2.03
     downstream
    -2.02
    stract
    -1.98
    fter
    -1.91
    Reloaded
    -1.86
    SPONSORED
    -1.82
    RESULTS
    -1.79
    etsk
    -1.79
    ).[
    -1.78
    cedented
    -1.76
    POSITIVE LOGITS
    アル
    2.12
    amara
    2.03
     yourself
    1.99
     Protector
    1.93
     Detective
    1.92
    anamo
    1.88
     yourselves
    1.86
     Travels
    1.83
     Volunte
    1.77
    ECK
    1.73
    Activations Density 0.240%

    No Known Activations