Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3164
    Prev
    Next
    INDEX
    Explanations

    timestamps or numerical data related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    0:0.19
    1:0.02
    2:0.06
    3:0.15
    4:0.05
    5:0.07
    6:0.04
    7:0.06
    8:0.10
    9:0.03
    10:0.16
    11:0.02
    Negative Logits
     Telephone
    -2.67
     radios
    -2.46
     chall
    -2.35
    fax
    -2.33
     violin
    -2.28
     Radio
    -2.28
    tel
    -2.23
     fortun
    -2.20
     hotline
    -2.20
     racket
    -2.20
    POSITIVE LOGITS
    Editor
    2.18
     Editorial
    2.08
     Seek
    2.08
    Pers
    2.05
     editors
    2.00
    ICLE
    1.99
    Adapt
    1.96
     writers
    1.94
     editorial
    1.94
     inherited
    1.93
    Activations Density 0.000%

    No Known Activations