© 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. 2-ATT-KK
    6. 22901
    Prev
    Next
    INDEX
    Explanations

    information related to specific locations and dates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    pronouns and their associations to possessive or relational contexts

    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
    0:0.08
    1:0.03
    2:0.16
    3:0.05
    4:0.02
    5:0.07
    6:0.05
    7:0.10
    8:0.07
    9:0.04
    10:0.17
    11:0.09
    Negative Logits
    etsk
    -0.96
     barr
    -0.79
    ollah
    -0.74
     bc
    -0.73
     DJ
    -0.73
     acqu
    -0.72
     gard
    -0.71
     Maid
    -0.71
    Downloadha
    -0.69
     Swanson
    -0.69
    POSITIVE LOGITS
    escription
    0.91
       
    0.82
    hor
    0.78
    ================
    0.78
    orio
    0.78
    fml
    0.77
    advertising
    0.76
    #$#$
    0.74
    uran
    0.73
    collar
    0.72
    Activations Density 0.092%

    No Known Activations