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

    Neuronpedia

    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. 43969
    Prev
    Next
    INDEX
    Explanations

    issues related to youth homelessness and its disproportionate impact on the transgender community

    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
    0:0.04
    1:0.01
    2:0.09
    3:0.11
    4:0.05
    5:0.07
    6:0.02
    7:0.03
    8:0.10
    9:0.11
    10:0.17
    11:0.13
    Negative Logits
    ascript
    -1.45
    jab
    -1.11
     disqualified
    -1.06
    Cola
    -1.06
    ceptive
    -1.05
    ゴン
    -1.05
     Adapter
    -1.03
    Attach
    -1.01
    ────
    -0.99
    gaard
    -0.99
    POSITIVE LOGITS
     worsen
    1.22
     trickle
    1.18
    isSpecialOrderable
    1.11
     exacerbate
    1.09
     exacerb
    1.07
     ripple
    1.06
     depress
    1.05
     suicides
    1.03
     Hait
    1.03
     surges
    1.03
    Activations Density 0.923%

    No Known Activations