© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42183
    Prev
    Next
    INDEX
    Explanations

    sentiments and descriptors of events, particularly relating to danger and disappointment

    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
    1:0.02
    2:0.18
    3:0.24
    4:0.08
    5:0.05
    6:0.06
    7:0.05
    8:0.06
    9:0.05
    10:0.08
    11:0.06
    Negative Logits
     :=
    -1.84
    ��
    -1.66
     <-
    -1.56
    rals
    -1.53
     denote
    -1.51
    quished
    -1.51
    utterstock
    -1.46
    \-
    -1.46
    onyms
    -1.44
    gdala
    -1.44
    POSITIVE LOGITS
    ".
    2.55
    "!
    2.44
    "
    2.42
    ".[
    2.40
    ",
    2.34
    "…
    2.31
    "...
    2.25
    ").
    2.22
    .""
    2.11
    ";
    2.07
    Activations Density 0.122%

    No Known Activations