© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21895
    Prev
    Next
    INDEX
    Explanations

    references to locations and establishments in Palo Alto

    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
    0:0.05
    1:0.03
    2:0.21
    3:0.06
    4:0.18
    5:0.06
    6:0.03
    7:0.04
    8:0.05
    9:0.14
    10:0.07
    11:0.04
    Negative Logits
    xual
    -1.29
     actionGroup
    -1.26
    blance
    -1.18
    iencies
    -1.16
    ilibrium
    -1.06
     IGF
    -1.04
    alion
    -1.04
    tein
    -1.04
     variance
    -1.04
     dysph
    -1.03
    POSITIVE LOGITS
    姫
    1.43
    sid
    1.19
    Gall
    1.14
    Utah
    1.12
    zan
    1.12
    sand
    1.10
    Gas
    1.09
    ople
    1.09
    bart
    1.08
    ossom
    1.07
    Activations Density 0.001%

    No Known Activations