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. 9-ATT-KK
    6. 114
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evaluations and assessments

    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
    0:0.04
    1:0.34
    2:0.05
    3:0.04
    4:0.04
    5:0.02
    6:0.14
    7:0.04
    8:0.02
    9:0.16
    10:0.03
    11:0.03
    Negative Logits
    闘
    -3.05
     guiActiveUn
    -3.03
    Bed
    -3.01
    76561
    -3.00
    ��
    -2.84
    obb
    -2.84
    fet
    -2.81
    specified
    -2.75
    ouf
    -2.74
    pend
    -2.73
    POSITIVE LOGITS
     great
    6.59
     GREAT
    6.18
    great
    5.81
     terrific
    5.65
     wonderful
    5.56
     tremendous
    5.46
     fantastic
    5.34
     Great
    5.26
    Great
    5.17
     incredible
    4.88
    Activations Density 0.040%

    No Known Activations