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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10280
    Prev
    Next
    INDEX
    Explanations

    present tense forms of the verb "to be" along with related auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.08
    2:0.17
    3:0.09
    4:0.02
    5:0.04
    6:0.09
    7:0.10
    8:0.07
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     trough
    -1.04
     rake
    -1.04
     >>>
    -0.90
    clave
    -0.86
     vine
    -0.83
    scan
    -0.81
    BuyableInstoreAndOnline
    -0.81
    inus
    -0.79
     boulder
    -0.79
    file
    -0.78
    POSITIVE LOGITS
     alike
    1.44
     respectively
    1.36
     ACTIONS
    1.10
    assadors
    1.09
    depending
    1.04
    iour
    1.04
    dain
    1.04
    issance
    1.02
    obic
    1.01
    estic
    0.94
    Activations Density 0.134%

    No Known Activations