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. 7-ATT-KK
    6. 18992
    Prev
    Next
    INDEX
    Explanations

    the action of movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.08
    4:0.08
    5:0.08
    6:0.09
    7:0.07
    8:0.08
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     Leilan
    -2.58
     Revenue
    -2.22
     acting
    -2.21
     choir
    -2.15
     racket
    -2.02
     Tycoon
    -1.94
     Franchise
    -1.93
    dylib
    -1.92
     solicitor
    -1.90
     �
    -1.89
    POSITIVE LOGITS
    brush
    2.17
    recomm
    2.16
    cz
    2.11
    scient
    2.05
    artz
    2.05
    abor
    2.03
    utorial
    2.03
    anch
    2.01
     Nicarag
    2.00
     cures
    2.00
    Activations Density 0.000%

    No Known Activations