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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22664
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by specific activities or actions that the subject does

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

    terms related to self-reference or positioning oneself

    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
    0:0.04
    1:0.02
    2:0.16
    3:0.04
    4:0.28
    5:0.06
    6:0.02
    7:0.02
    8:0.10
    9:0.13
    10:0.05
    11:0.02
    Negative Logits
     Gron
    -1.40
     directions
    -1.35
     mosquit
    -1.27
    ��
    -1.26
     Router
    -1.24
     modification
    -1.23
    Motor
    -1.22
     apart
    -1.19
    Pac
    -1.19
    RN
    -1.18
    POSITIVE LOGITS
    anguage
    2.00
    ioxide
    1.77
    hire
    1.70
    enment
    1.69
    lees
    1.56
    FTWARE
    1.56
    enium
    1.56
    gage
    1.53
    geant
    1.51
    itte
    1.49
    Activations Density 0.011%

    No Known Activations