© 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. 22512
    Prev
    Next
    INDEX
    Explanations

    potential threats or vulnerabilities related to security and safety, such as in the context of technology, disaster preparedness, or societal structures

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

    occurrences of the word "to" in various contexts

    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
    0:0.06
    1:0.03
    2:0.11
    3:0.06
    4:0.32
    5:0.03
    6:0.03
    7:0.02
    8:0.14
    9:0.09
    10:0.04
    11:0.02
    Negative Logits
    minus
    -1.51
    itzer
    -1.46
    llor
    -1.44
    Merit
    -1.42
    rier
    -1.40
    ciation
    -1.38
    NAS
    -1.38
    ren
    -1.36
    cknowled
    -1.35
    arest
    -1.34
    POSITIVE LOGITS
    ドラ
    1.46
    itely
    1.37
     Lyme
    1.35
     corrective
    1.28
     throats
    1.27
     gland
    1.25
     Plane
    1.23
     glands
    1.19
     Potential
    1.18
    entin
    1.16
    Activations Density 0.004%

    No Known Activations