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. 3-ATT-KK
    6. 10465
    Prev
    Next
    INDEX
    Explanations

    verbs that convey actions related to helping, improving, or causing change

    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
    0:0.06
    1:0.05
    2:0.08
    3:0.03
    4:0.04
    5:0.19
    6:0.09
    7:0.08
    8:0.12
    9:0.04
    10:0.13
    11:0.04
    Negative Logits
     Lv
    -1.57
     Rothschild
    -1.53
     Lands
    -1.52
     Bild
    -1.47
     Naj
    -1.45
     Nicol
    -1.40
    enger
    -1.33
     Ago
    -1.28
     Mort
    -1.28
     Glac
    -1.28
    POSITIVE LOGITS
    スト
    1.47
     shortcuts
    1.47
     PROG
    1.46
     traps
    1.42
    gging
    1.42
    zzle
    1.41
    ��
    1.38
    aroo
    1.35
    aching
    1.33
    asionally
    1.32
    Activations Density 0.196%

    No Known Activations