© 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. 2-ATT-KK
    11. 15224
    Prev
    Next
    INDEX
    Explanations

    different categories of text based on the nature of the content, such as reporting news, discussing political figures, business presentations or event coverage in the media

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.03
    2:0.11
    3:0.15
    4:0.08
    5:0.13
    6:0.04
    7:0.02
    8:0.10
    9:0.13
    10:0.06
    11:0.03
    Negative Logits
    eworks
    -1.66
    lees
    -1.50
     Halls
    -1.40
    falls
    -1.20
     Tours
    -1.17
    iences
    -1.14
    stad
    -1.14
    ICES
    -1.13
    ques
    -1.13
     Ventures
    -1.11
    POSITIVE LOGITS
    peat
    1.57
    ailable
    1.31
    ivable
    1.30
    ritten
    1.29
     fold
    1.27
    exclusive
    1.27
    azo
    1.21
    achable
    1.20
    emonic
    1.17
     combination
    1.17
    Activations Density 0.067%

    No Known Activations