INDEX

Explanations

phrases that express time-related concepts or durations

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

"a" followed by time-related words

np_acts-logits-general · gemini-2.0-flash

a followed by time

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

 newOwner

-0.65

$_['

-0.62

ViewImports

-0.62

MessageTagHelper

-0.57

'][$

-0.54

ImageField

-0.54

 '\\;'

-0.52

 betweenstory

-0.52

TintMode

-0.51

webElementXpaths

-0.51

POSITIVE LOGITS

 minute

2.42

 minutes

2.39

 moment

2.24

minute

2.07

 moments

2.02

 Minutes

1.92

moment

1.91

minutes

1.88

 seconds

1.85

 Moment

1.84

Activations Density 0.633%

phrases that express time-related concepts or durations

"a" followed by time-related words

a followed by time

No Comments

No Known Activations