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. 3-ATT-KK
    6. 8404
    Prev
    Next
    INDEX
    Explanations

    references to location, context, or the presence of specific subjects within a sentence

    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
    1:0.15
    2:0.16
    3:0.03
    4:0.01
    5:0.02
    6:0.07
    7:0.09
    8:0.17
    9:0.03
    10:0.06
    11:0.14
    Negative Logits
     extrad
    -1.17
    ��
    -1.11
    depth
    -1.10
    earth
    -1.07
     Rud
    -1.06
    liga
    -1.05
     SUR
    -1.04
    aten
    -1.03
     TRI
    -1.00
     Ratio
    -1.00
    POSITIVE LOGITS
    ppy
    1.36
    }\
    1.20
     nor
    1.19
    icable
    1.18
    }.
    1.14
    }"
    1.13
     sexes
    1.08
    _>
    1.07
    selves
    1.06
    }
    1.05
    Activations Density 0.063%

    No Known Activations