© 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. 43415
    Prev
    Next
    INDEX
    Explanations

    references to various entities and their relationships, particularly within the context of startups and economic discussions

    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
    1:0.01
    2:0.06
    3:0.07
    4:0.07
    5:0.06
    6:0.40
    7:0.02
    8:0.04
    9:0.04
    10:0.10
    11:0.05
    Negative Logits
     tolerance
    -1.28
     iod
    -1.24
    alsh
    -1.22
    pection
    -1.18
    izabeth
    -1.18
     recognition
    -1.12
     Sneak
    -1.12
     compressor
    -1.11
     aspiration
    -1.10
     breadth
    -1.09
    POSITIVE LOGITS
    eps
    1.34
    ales
    1.30
    yrs
    1.25
     entail
    1.24
    auld
    1.22
    represent
    1.22
    stros
    1.22
    ypes
    1.22
    ernels
    1.21
    amas
    1.21
    Activations Density 0.083%

    No Known Activations