© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20730
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.09
    2:0.06
    3:0.11
    4:0.07
    5:0.08
    6:0.09
    7:0.07
    8:0.07
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
    Reviewer
    -2.60
     Reader
    -2.40
     Vietnam
    -2.34
     readers
    -2.26
     detectives
    -2.25
     Ireland
    -2.25
     GOODMAN
    -2.22
     Warner
    -2.20
     Byrne
    -2.17
     reader
    -2.14
    POSITIVE LOGITS
     Chocobo
    3.42
    adish
    3.19
    eco
    2.68
    azard
    2.53
    emo
    2.47
    icter
    2.47
    dfx
    2.46
    emp
    2.46
    algia
    2.44
    ealous
    2.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.