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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42877
    Prev
    Next
    INDEX
    Explanations

    first-person narrative elements related to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.01
    2:0.14
    3:0.19
    4:0.12
    5:0.07
    6:0.02
    7:0.06
    8:0.04
    9:0.10
    10:0.10
    11:0.06
    Negative Logits
    cil
    -1.42
    )</
    -1.36
    Elsewhere
    -1.25
    "?
    -1.22
    "},{"
    -1.22
    "}],"
    -1.19
    ?」
    -1.15
    redo
    -1.14
     emerges
    -1.14
     embattled
    -1.13
    POSITIVE LOGITS
     myself
    1.69
    carb
    1.28
    acl
    1.23
    igslist
    1.20
     bc
    1.19
    debian
    1.16
     FF
    1.16
     my
    1.13
     BF
    1.12
     Shinra
    1.12
    Activations Density 0.596%

    No Known Activations