© 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. 21852
    Prev
    Next
    INDEX
    Explanations

    phrases related to disruption or interruption in various contexts

    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
    2:0.19
    3:0.04
    4:0.21
    5:0.06
    6:0.03
    7:0.03
    8:0.09
    9:0.14
    10:0.05
    11:0.02
    Negative Logits
    sonian
    -1.48
    orthy
    -1.42
    NAS
    -1.37
    ilts
    -1.35
    nis
    -1.34
    sa
    -1.31
     proudly
    -1.30
    saf
    -1.30
    uliffe
    -1.30
     boldly
    -1.30
    POSITIVE LOGITS
     disruptive
    1.40
     wavelength
    1.36
     disruption
    1.34
     digestion
    1.31
     disturbance
    1.28
    vous
    1.28
     communication
    1.27
     congestion
    1.27
     electromagnetic
    1.25
     disease
    1.25
    Activations Density 0.010%

    No Known Activations