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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 20125
    Prev
    Next
    INDEX
    Explanations

    references to unusual or controversial legal defenses

    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
    0:0.04
    1:0.01
    2:0.04
    3:0.10
    4:0.04
    5:0.11
    6:0.02
    7:0.02
    8:0.09
    9:0.21
    10:0.18
    11:0.08
    Negative Logits
    ahime
    -1.91
     mathemat
    -1.47
     Centauri
    -1.42
    equality
    -1.42
    izontal
    -1.40
     calcul
    -1.36
     moderation
    -1.32
     transitions
    -1.30
     Alphabet
    -1.29
     incumb
    -1.28
    POSITIVE LOGITS
     panicked
    1.57
     aborted
    1.53
     horrified
    1.48
     later
    1.42
     rapist
    1.42
     felon
    1.41
     robbery
    1.33
     murderer
    1.32
     assailant
    1.32
     intruder
    1.31
    Activations Density 0.868%

    No Known Activations