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. 9-ATT-KK
    6. 33
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or their circumstances in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attends to the last character in a sentence from preceding tokens.

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.14
    1:0.02
    2:0.18
    3:0.07
    4:0.03
    5:0.05
    6:0.06
    7:0.06
    8:0.20
    9:0.07
    10:0.04
    11:0.03
    Negative Logits
     checkpoints
    -3.77
    Iowa
    -3.73
     checkpoint
    -3.41
     Boone
    -3.29
     militia
    -3.28
     Militia
    -3.25
     UAE
    -3.23
    Utah
    -3.17
     Jindal
    -3.15
     Benghazi
    -3.13
    POSITIVE LOGITS
     Freud
    8.30
     Psycho
    5.02
     psycho
    4.62
     psych
    4.49
     Psych
    4.35
    Psych
    4.17
     psychiatrists
    4.02
     Gö
    3.99
    Fre
    3.93
     psychiatry
    3.91
    Activations Density 0.000%

    No Known Activations