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. 5-ATT-KK
    6. 44036
    Prev
    Next
    INDEX
    Explanations

    references to a specific male individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.05
    1:0.02
    2:0.05
    3:0.06
    4:0.06
    5:0.15
    6:0.06
    7:0.01
    8:0.13
    9:0.13
    10:0.11
    11:0.13
    Negative Logits
    NetMessage
    -1.46
    ivation
    -1.29
    velop
    -1.28
    urious
    -1.28
    PsyNetMessage
    -1.26
    paren
    -1.25
    need
    -1.24
    hered
    -1.23
    omen
    -1.22
    cape
    -1.21
    POSITIVE LOGITS
     sacked
    1.40
     secondly
    1.22
     furthermore
    1.20
     Franks
    1.19
    senal
    1.18
     Illust
    1.15
     Senior
    1.13
     flanked
    1.10
     murdered
    1.09
     Originally
    1.09
    Activations Density 0.071%

    No Known Activations