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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 44275
    Prev
    Next
    INDEX
    Explanations

    patterns of observation and visual assessment

    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
    0:0.02
    1:0.02
    2:0.07
    3:0.18
    4:0.11
    5:0.03
    6:0.08
    7:0.20
    8:0.04
    9:0.04
    10:0.07
    11:0.09
    Negative Logits
    arsity
    -1.79
     ancest
    -1.59
    otyp
    -1.58
    "},"
    -1.57
    ificantly
    -1.55
     uncond
    -1.52
    ocally
    -1.49
    erate
    -1.46
    etermined
    -1.44
    omaly
    -1.43
    POSITIVE LOGITS
     Subtle
    1.76
     Youtube
    1.53
     Pinterest
    1.44
     Pascal
    1.44
     circles
    1.34
     Clip
    1.34
    paren
    1.33
     ripple
    1.32
     irony
    1.32
     Journals
    1.32
    Activations Density 0.016%

    No Known Activations