© 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. 9-ATT-KK
    11. 18939
    Prev
    Next
    INDEX
    Explanations

    connections between various forms of support and needs in community contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.06
    3:0.23
    4:0.02
    5:0.05
    6:0.02
    7:0.05
    8:0.04
    9:0.02
    10:0.38
    11:0.01
    Negative Logits
     desired
    -2.24
     wanted
    -2.23
    iani
    -2.13
    actly
    -2.10
    needed
    -2.04
     spoil
    -2.03
    sorry
    -1.98
     suspect
    -1.96
     frontrunner
    -1.95
     winner
    -1.87
    POSITIVE LOGITS
     outreach
    2.76
     endeavors
    2.46
     partnerships
    2.38
     methods
    2.31
     initiatives
    2.23
     efforts
    2.22
     mechanisms
    2.22
    pmwiki
    2.21
     collaborative
    2.17
     seminars
    2.16
    Activations Density 0.188%

    No Known Activations