INDEX

Explanations

instances of the word "down" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

出版年

-0.66

>-->

-0.65

%)$

-0.65

pense

-0.63

]='\

-0.63

xture

-0.62

(&:

-0.62

++]=

-0.62

tellations

-0.59

letcher

-0.59

POSITIVE LOGITS

down

4.42

Down

4.37

 down

4.36

 Down

4.25

DOWN

3.88

 DOWN

3.85

downs

3.27

 downs

3.00

Downs

2.70

ダウン

2.66

Activations Density 0.068%

instances of the word "down" in various contexts

No Comments

No Known Activations