© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43093
    Prev
    Next
    INDEX
    Explanations

    references to images and photos in a text

    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
    0:0.01
    1:0.01
    2:0.06
    3:0.04
    4:0.03
    5:0.02
    6:0.40
    7:0.13
    8:0.03
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
    cot
    -1.44
     Diesel
    -1.26
    SQL
    -1.17
    voy
    -1.14
     TAMADRA
    -1.14
     repentance
    -1.12
     tast
    -1.12
    sky
    -1.11
    obos
    -1.11
    yip
    -1.10
    POSITIVE LOGITS
    enhagen
    1.35
    fecture
    1.32
    nesses
    1.31
    usalem
    1.28
    uers
    1.25
    nants
    1.24
    ropolitan
    1.23
    rison
    1.23
    arez
    1.23
    prus
    1.23
    Activations Density 0.005%

    No Known Activations