INDEX

Explanations

references to attention and its various implications in different contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lehman

-0.63

camore

-0.63

raborty

-0.62

 Wadsworth

-0.61

 Gefühle

-0.61

谷川

-0.61

 Whitehead

-0.61

 maestra

-0.60

 Silverado

-0.60

 Roos

-0.60

POSITIVE LOGITS

 attention

2.10

 Attention

1.91

attention

1.75

 ATTENTION

1.74

Attention

1.68

 attentions

1.57

ATTENTION

1.48

attenzione

1.25

 Atención

1.24

 atención

1.15

Activations Density 0.044%

references to attention and its various implications in different contexts

No Comments

No Known Activations