Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22455
    Prev
    Next
    INDEX
    Explanations

    emotional and mental states

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

    words that describe mental states or conditions

    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
    0:0.03
    1:0.02
    2:0.21
    3:0.04
    4:0.19
    5:0.07
    6:0.03
    7:0.02
    8:0.14
    9:0.13
    10:0.05
    11:0.02
    Negative Logits
    IRC
    -1.31
    checks
    -1.24
    WT
    -1.18
     redistributed
    -1.16
     github
    -1.15
    INC
    -1.15
    awn
    -1.15
    Zip
    -1.13
     Zac
    -1.12
     repo
    -1.11
    POSITIVE LOGITS
    poral
    1.31
    osterone
    1.25
     Anxiety
    1.24
     unfocusedRange
    1.24
    Interstitial
    1.21
    utics
    1.20
    ombat
    1.19
    abis
    1.19
    tro
    1.18
     Revenge
    1.18
    Activations Density 0.006%

    No Known Activations