© 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. 5-ATT-KK
    11. 28395
    Prev
    Next
    INDEX
    Explanations

    questions about identity and self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.08
    4:0.20
    5:0.03
    6:0.03
    7:0.23
    8:0.08
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
    etheless
    -1.96
    esters
    -1.80
    adr
    -1.70
    cit
    -1.68
    asury
    -1.68
    abase
    -1.68
    avery
    -1.68
    ravel
    -1.67
    vati
    -1.61
    ItemTracker
    -1.61
    POSITIVE LOGITS
     advis
    1.97
     aloud
    1.91
     faults
    1.74
     deeds
    1.68
     names
    1.64
     ______
    1.63
     hazards
    1.62
     kisses
    1.60
     subscript
    1.59
     secrets
    1.55
    Activations Density 0.016%

    No Known Activations