© 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. 5-ATT-KK
    11. 35846
    Prev
    Next
    INDEX
    Explanations

    references to personal struggles and issues related to identity and mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.02
    1:0.02
    2:0.11
    3:0.06
    4:0.21
    5:0.02
    6:0.09
    7:0.23
    8:0.04
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    ortium
    -1.87
    Austral
    -1.64
    GROUP
    -1.57
    assadors
    -1.54
    emed
    -1.54
    arers
    -1.53
    study
    -1.53
    saf
    -1.53
    arnaev
    -1.51
     beneficiaries
    -1.51
    POSITIVE LOGITS
     hardness
    2.11
     breakup
    1.99
     knots
    1.78
     difficulty
    1.76
     stiff
    1.74
     difficulties
    1.73
     fragmentation
    1.71
     inconsistency
    1.70
     stiffness
    1.69
     deform
    1.68
    Activations Density 0.005%

    No Known Activations