INDEX

Explanations

repetitive phrases or expressions of action, particularly variations of the word "do."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CloseOperation

-0.99

elemField

-0.70

出版年

-0.68

ysacchar

-0.64

 soient

-0.63

\{\\

-0.62

:✨

-0.62

accharides

-0.62

談社

-0.61

ItemBackground

-0.60

POSITIVE LOGITS

 indeed

1.03

 seem

0.85

 have

0.82

not

0.75

 need

0.73

 however

0.72

 deserve

0.70

NOT

0.66

 contain

0.65

 still

0.65

Activations Density 0.086%

repetitive phrases or expressions of action, particularly variations of the word "do."

No Comments

No Known Activations