© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43932
    Prev
    Next
    INDEX
    Explanations

    pronouns and forms of the verb "to be" in relation to personal and societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.05
    3:0.13
    4:0.12
    5:0.05
    6:0.03
    7:0.23
    8:0.08
    9:0.07
    10:0.08
    11:0.09
    Negative Logits
    ander
    -1.47
    Reviewer
    -1.46
    riad
    -1.44
    othing
    -1.42
    apego
    -1.41
    ÍÍ
    -1.35
    advant
    -1.35
    ========
    -1.34
    selage
    -1.33
    �
    -1.32
    POSITIVE LOGITS
     renegoti
    1.79
     visas
    1.41
     pencil
    1.41
     expiration
    1.39
    lock
    1.38
     subpoen
    1.37
     wedge
    1.34
    interrupted
    1.33
     documentaries
    1.30
     tamp
    1.27
    Activations Density 0.007%

    No Known Activations