INDEX

Explanations

keywords indicating data or performance metrics

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

:\\

-0.58

voorbeeld

-0.58

 Kindly

-0.58

 Acerca

-0.58

},{

-0.56

 coordonnées

-0.55

 ་་

-0.55

 󰀄

-0.54

)、

-0.54

**/

-0.53

POSITIVE LOGITS

 they

1.13

it

1.12

we

1.12

you

1.05

the

1.04

he

1.03

0.94

0.93

 there

0.91

all

0.82

Activations Density 0.377%

keywords indicating data or performance metrics

No Comments

No Known Activations