© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43075
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with individuals

    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
    1:0.04
    2:0.06
    3:0.06
    4:0.03
    5:0.04
    6:0.46
    7:0.04
    8:0.05
    9:0.05
    10:0.06
    11:0.04
    Negative Logits
     tumble
    -1.29
     wizards
    -1.22
    humans
    -1.19
    pmwiki
    -1.19
     mantle
    -1.19
     docks
    -1.15
     rectangle
    -1.12
    Args
    -1.11
    rawdownloadcloneembedreportprint
    -1.11
     garment
    -1.11
    POSITIVE LOGITS
    ufact
    1.44
     Sear
    1.40
    llor
    1.32
    ohyd
    1.29
    iannopoulos
    1.29
    ouf
    1.25
    uzz
    1.25
    ICAN
    1.25
    OY
    1.22
    achy
    1.20
    Activations Density 0.064%

    No Known Activations