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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7070
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their interconnections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.02
    2:0.17
    3:0.12
    4:0.10
    5:0.04
    6:0.10
    7:0.02
    8:0.07
    9:0.07
    10:0.06
    11:0.07
    Negative Logits
     Jagu
    -1.49
    hap
    -1.46
     Gerr
    -1.41
     Schne
    -1.36
    ADRA
    -1.27
     Temper
    -1.27
     Fraz
    -1.27
     Admir
    -1.27
     Beet
    -1.25
    BIP
    -1.25
    POSITIVE LOGITS
    "}
    2.02
     etc
    2.02
    etc
    1.99
    })
    1.87
    }.
    1.81
    ]);
    1.75
    )?
    1.64
    ornia
    1.64
    dq
    1.64
    },
    1.61
    Activations Density 0.024%

    No Known Activations