INDEX

Explanations

time-related terms and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.87

 بيها

-0.86

 виправивши

-0.82

setVerticalGroup

-0.81

TagMode

-0.78

^(@)

-0.78

$_"

-0.78

ſy

-0.76

TITUDE

-0.75

Eksterne

-0.75

POSITIVE LOGITS

 hours

1.62

 seconds

1.51

 minutes

1.41

 months

1.35

seconds

1.34

 Hours

1.32

Hours

1.32

hours

1.29

 weeks

1.25

 HOURS

1.24

Activations Density 0.122%

time-related terms and measurements

No Comments

No Known Activations