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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22059
    Prev
    Next
    INDEX
    Explanations

    themes of social injustice and community displacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.05
    3:0.07
    4:0.03
    5:0.10
    6:0.20
    7:0.06
    8:0.05
    9:0.06
    10:0.15
    11:0.05
    Negative Logits
    itled
    -1.71
    translation
    -1.62
    ETA
    -1.62
    alloween
    -1.57
    reenshots
    -1.57
    isu
    -1.54
    english
    -1.47
    xtap
    -1.45
    ategories
    -1.44
    surprisingly
    -1.41
    POSITIVE LOGITS
    )."
    3.48
    .'"
    3.02
     …"
    2.96
    '."
    2.96
    ..."
    2.94
    .")
    2.82
    .""
    2.79
    ."[
    2.77
    ]."
    2.60
    ."
    2.51
    Activations Density 0.350%

    No Known Activations