INDEX

Explanations

references to dates and time periods in a legal or review context

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

Tokens appearing before numbers

np_acts-logits-general · gemini-2.0-flash

years 2006-2019

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.86

-0.78

-0.71

-0.70

 ۱۹

-0.66

-0.61

-0.60

 nine

-0.60

POSITIVE LOGITS

TagMode

1.20

CloseOperation

1.14

 صوتيه

1.04

 '\\;'

0.95

 Roskov

0.94

 مرئيه

0.93

HideFlags

0.92

 Baillargeon

0.91

Personensuche

0.91

 auffi

0.90

Activations Density 0.193%

references to dates and time periods in a legal or review context

Tokens appearing before numbers

years 2006-2019

No Comments

No Known Activations