© 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. 43256
    Prev
    Next
    INDEX
    Explanations

    mentions of people and organizations involved in news-related photography or reporting

    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
    0:0.22
    1:0.25
    2:0.03
    3:0.04
    4:0.02
    5:0.17
    6:0.02
    7:0.02
    8:0.07
    9:0.07
    10:0.02
    11:0.02
    Negative Logits
    planet
    -2.24
    akin
    -1.88
    soft
    -1.83
    guns
    -1.82
    feat
    -1.81
    match
    -1.81
    yth
    -1.79
    oqu
    -1.77
    axis
    -1.75
    alter
    -1.75
    POSITIVE LOGITS
     The
    2.42
     Some
    2.41
     Bottom
    2.30
     Blink
    2.30
     Rear
    2.28
     Another
    2.26
     Leilan
    2.26
     An
    2.23
     Wait
    2.22
     Mul
    2.19
    Activations Density 0.102%

    No Known Activations