© 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. 15693
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to analyzing discussions or reports, particularly focusing on failures, responses, and implications within political or business contexts

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.04
    1:0.02
    2:0.24
    3:0.05
    4:0.13
    5:0.07
    6:0.02
    7:0.03
    8:0.10
    9:0.18
    10:0.04
    11:0.02
    Negative Logits
    版
    -1.81
    aucas
    -1.36
    ────
    -1.35
    thia
    -1.30
    perture
    -1.28
    hern
    -1.28
    vice
    -1.21
    reme
    -1.19
    cyclop
    -1.14
    porting
    -1.13
    POSITIVE LOGITS
     digestion
    1.24
    メ
    1.23
     cycle
    1.12
     concentration
    1.12
     effectiveness
    1.11
     Huck
    1.10
     Reincarn
    1.09
     circumstance
    1.08
    AFTA
    1.08
     Silence
    1.08
    Activations Density 0.016%

    No Known Activations