© 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. 2-ATT-KK
    11. 21759
    Prev
    Next
    INDEX
    Explanations

    occurrences of statistical or numeric information related to data and analysis

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.06
    1:0.02
    2:0.05
    3:0.46
    4:0.05
    5:0.06
    6:0.04
    7:0.03
    8:0.05
    9:0.07
    10:0.05
    11:0.02
    Negative Logits
    ilies
    -1.35
     Zur
    -1.28
     favorites
    -1.21
     Supplemental
    -1.20
     STA
    -1.19
     cousins
    -1.18
    aters
    -1.18
     prevailed
    -1.17
     Compliance
    -1.16
     Cance
    -1.16
    POSITIVE LOGITS
     imaginable
    1.82
    except
    1.55
    omnia
    1.50
    acca
    1.49
     conceivable
    1.44
    oso
    1.42
     except
    1.37
    inery
    1.35
    perty
    1.34
    ixt
    1.30
    Activations Density 0.158%

    No Known Activations