© 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. 2-ATT-KK
    11. 22586
    Prev
    Next
    INDEX
    Explanations

    instances of words related to impactful physical actions or events such as hitting, getting hit, injuries, accidents, medical care, and arrests in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    prepositions, especially "by" and "out"

    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
    0:0.07
    1:0.02
    2:0.11
    3:0.05
    4:0.32
    5:0.04
    6:0.02
    7:0.01
    8:0.16
    9:0.08
    10:0.04
    11:0.02
    Negative Logits
    behind
    -1.58
    iltr
    -1.55
    culated
    -1.50
    pired
    -1.41
    liness
    -1.40
    kered
    -1.40
    grand
    -1.36
    ever
    -1.35
     symb
    -1.35
    kept
    -1.33
    POSITIVE LOGITS
    ��
    1.38
     therap
    1.35
    Attach
    1.33
     blot
    1.30
     Dems
    1.27
     injury
    1.24
     Heller
    1.23
     liberals
    1.20
     heap
    1.20
     Shogun
    1.19
    Activations Density 0.022%

    No Known Activations