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. 5-ATT-KK
    6. 43597
    Prev
    Next
    INDEX
    Explanations

    numerical or pricing details associated with products and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.41
    2:0.04
    3:0.04
    4:0.02
    5:0.11
    6:0.05
    7:0.01
    8:0.05
    9:0.04
    10:0.05
    11:0.03
    Negative Logits
    ��
    -1.78
     Ao
    -1.77
    amate
    -1.73
    ebus
    -1.70
    orsche
    -1.68
    ���
    -1.65
    ��
    -1.61
     Ake
    -1.61
    pb
    -1.61
     Acc
    -1.61
    POSITIVE LOGITS
    2013
    2.40
    stars
    2.16
    Star
    2.15
    13
    2.08
    iko
    1.98
    Jer
    1.97
    star
    1.94
    ksh
    1.90
    Stars
    1.90
    taboola
    1.80
    Activations Density 0.049%

    No Known Activations