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. 3-ATT-KK
    6. 10376
    Prev
    Next
    INDEX
    Explanations

    and assess the presence of adjectives and descriptions related to purposefulness and function

    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
    0:0.02
    1:0.03
    2:0.08
    3:0.23
    4:0.02
    5:0.03
    6:0.20
    7:0.09
    8:0.05
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
    aspberry
    -1.37
    ISON
    -1.35
    imar
    -1.33
    NA
    -1.30
    ITH
    -1.30
    CN
    -1.29
    risome
    -1.24
    apeake
    -1.24
    wikipedia
    -1.23
     CONTR
    -1.22
    POSITIVE LOGITS
     guiActiveUnfocused
    1.60
    els
    1.38
    forts
    1.23
    ttes
    1.20
    quartered
    1.19
    isans
    1.18
    agers
    1.12
    rocket
    1.12
     persuasion
    1.12
    pants
    1.12
    Activations Density 0.025%

    No Known Activations