INDEX

Explanations

elements that signify shared experiences or social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 насељу

-0.63

fromnode

-0.63

 aveug

-0.59

 aéri

-0.56

 magát

-0.55

 kendini

-0.54

 själv

-0.54

 fråga

-0.54

 själ

-0.53

 fallu

-0.52

POSITIVE LOGITS

 together

1.57

 juntos

1.40

 collectively

1.38

 jointly

1.31

together

1.27

 Together

1.26

Together

1.25

 TOGETHER

1.20

 saling

1.19

 nhau

1.13

Activations Density 0.402%

elements that signify shared experiences or social interactions

No Comments

No Known Activations