© 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. 21794
    Prev
    Next
    INDEX
    Explanations

    phrases involving commands or directives

    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
    0:0.06
    1:0.02
    2:0.03
    3:0.06
    4:0.30
    5:0.07
    6:0.03
    7:0.02
    8:0.23
    9:0.06
    10:0.05
    11:0.02
    Negative Logits
    mouth
    -1.64
    spring
    -1.42
    idth
    -1.37
    peak
    -1.24
    dash
    -1.21
    inges
    -1.17
     boast
    -1.17
     depress
    -1.16
    feat
    -1.14
    pring
    -1.14
    POSITIVE LOGITS
     Hort
    1.39
     postp
    1.36
    Continue
    1.27
    ODY
    1.25
    dule
    1.23
    otiation
    1.23
    �
    1.23
    FORMATION
    1.22
     withd
    1.22
    NRS
    1.18
    Activations Density 0.013%

    No Known Activations