INDEX

Explanations

indicators of completeness or totality in contexts that involve data or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

instead

-0.41

出版年

-0.38

 instead

-0.38

fake

-0.35

 tưởng

-0.34

迎

-0.33

 вместо

-0.32

 fake

-0.32

behind

-0.32

laud

-0.32

POSITIVE LOGITS

تقاوى

0.65

 surviving

0.48

matchCondition

0.46

 verfügb

0.46

 CreateTagHelper

0.45

routeProvider

0.45

libft

0.44

 obecnie

0.44

 actualmente

0.44

 conceivable

0.44

Activations Density 0.856%

indicators of completeness or totality in contexts that involve data or lists

No Comments

No Known Activations