INDEX

Explanations

references to scientific studies or research

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

"study"

np_acts-logits-general · gemini-2.0-flash

study of

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.84

LikeLike

-0.66

vska

-0.65

cett

-0.64

minHeight

-0.63

ว่าง

-0.62

}_{(

-0.62

Zha

-0.61

pherals

-0.61

ReusableCell

-0.61

POSITIVE LOGITS

STUDY

1.18

study

1.17

 studies

1.14

 study

1.12

studies

1.11

 Study

1.09

Study

1.04

 STUDY

1.04

 studie

1.01

 Studying

1.00

Activations Density 0.136%

references to scientific studies or research

"study"

study of

No Comments

No Known Activations