INDEX

Explanations

phrases indicating understanding or clarity regarding concepts

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

"make sense" or variations

np_acts-logits-general · gemini-2.0-flash

make sense phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 nahilalakip

-0.75

 &___

-0.66

 oprot

-0.64

 saites

-0.62

 متعلقه

-0.61

 Heights

-0.56

 للمعارف

-0.56

ulet

-0.55

RegressionTest

-0.55

titleMargin

-0.53

POSITIVE LOGITS

 sense

2.31

sense

1.80

 SENSE

1.57

 sentido

1.49

 Sense

1.48

Sense

1.38

 senso

1.28

 senses

1.21

 sens

1.09

ense

0.96

Activations Density 0.130%

phrases indicating understanding or clarity regarding concepts

"make sense" or variations

make sense phrases

No Comments

No Known Activations