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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43347
    Prev
    Next
    INDEX
    Explanations

    URLs and web references indicating resources or sources of information

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.15
    4:0.12
    5:0.04
    6:0.12
    7:0.11
    8:0.03
    9:0.05
    10:0.09
    11:0.11
    Negative Logits
     Canaver
    -1.27
     divorced
    -1.25
     grandchildren
    -1.23
    ebted
    -1.23
     outwe
    -1.22
     embattled
    -1.22
     Adin
    -1.20
     TAMADRA
    -1.20
     signaling
    -1.19
     allegiance
    -1.18
    POSITIVE LOGITS
    Reviewer
    1.75
    Creat
    1.62
    Names
    1.61
     google
    1.61
    facebook
    1.58
    wiki
    1.55
    atre
    1.50
    pedia
    1.48
    Studio
    1.44
    emp
    1.42
    Activations Density 0.007%

    No Known Activations