INDEX

Explanations

references to actions and their consequences, emphasizing occurrences and substances

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

followed by "to" (often infinitive verbs)

np_acts-logits-general · gemini-2.0-flash

happened to be going to

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Roskov

-0.93

 surla

-0.92

 <>",

-0.90

GraphicsUnit

-0.90

fromnode

-0.86

 resourceCulture

-0.85

:✨

-0.83

はじめに

-0.81

 CreateTagHelper

-0.80

PreferredItem

-0.78

POSITIVE LOGITS

to

2.82

 να

1.52

să

1.16

to

1.02

 чтобы

0.88

 להיות

0.86

 להת

0.84

ที่จะ

0.84

 לה

0.82

tobe

0.80

Activations Density 2.070%

references to actions and their consequences, emphasizing occurrences and substances

followed by "to" (often infinitive verbs)

happened to be going to

No Comments

No Known Activations