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. 5-ATT-KK
    6. 2849
    Prev
    Next
    INDEX
    Explanations

    the mention of authoritative figures or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.07
    2:0.06
    3:0.07
    4:0.07
    5:0.09
    6:0.10
    7:0.10
    8:0.06
    9:0.12
    10:0.09
    11:0.07
    Negative Logits
     Detention
    -1.61
    interstitial
    -1.55
    ��
    -1.47
     Supply
    -1.44
    Interstitial
    -1.42
     Selling
    -1.25
    �
    -1.25
    』
    -1.25
    ��
    -1.24
     mend
    -1.24
    POSITIVE LOGITS
    ources
    1.49
    rone
    1.45
    hift
    1.45
    sonian
    1.44
     GOODMAN
    1.37
    borgh
    1.35
    OGR
    1.33
    rop
    1.32
    izont
    1.32
    ocr
    1.31
    Activations Density 0.000%

    No Known Activations