© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 40840
    Prev
    Next
    INDEX
    Explanations

    quotation marks and phrases indicating published works or formal statements

    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
    0:0.02
    1:0.02
    2:0.25
    3:0.10
    4:0.08
    5:0.05
    6:0.03
    7:0.04
    8:0.06
    9:0.05
    10:0.13
    11:0.10
    Negative Logits
     buds
    -1.60
     unreliable
    -1.51
     nonexistent
    -1.45
     bona
    -1.41
    hops
    -1.40
    fired
    -1.39
    nings
    -1.36
     overpowered
    -1.35
    anging
    -1.34
     notwithstanding
    -1.34
    POSITIVE LOGITS
    zinski
    1.73
    ?????-?????-
    1.65
    selage
    1.65
    Db
    1.64
    ashington
    1.64
    iframe
    1.64
     captcha
    1.53
     dx
    1.53
    ?????-
    1.51
    cms
    1.49
    Activations Density 0.000%

    No Known Activations