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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21736
    Prev
    Next
    INDEX
    Explanations

    terms associated with feelings of hopelessness and despair

    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
    1:0.03
    2:0.18
    3:0.07
    4:0.17
    5:0.06
    6:0.03
    7:0.03
    8:0.07
    9:0.15
    10:0.05
    11:0.03
    Negative Logits
    soDeliveryDate
    -1.31
    aea
    -1.28
    Asset
    -1.26
     guideline
    -1.19
    minus
    -1.16
    Maps
    -1.13
    版
    -1.10
    ALT
    -1.09
     coordin
    -1.08
     authorised
    -1.07
    POSITIVE LOGITS
     Despair
    1.47
    gery
    1.20
     boredom
    1.18
     Souls
    1.14
     loneliness
    1.14
     unbeliev
    1.13
     delusion
    1.12
     grasping
    1.10
    horse
    1.09
     Syndrome
    1.09
    Activations Density 0.003%

    No Known Activations