INDEX

Explanations

instances of the word "used" along with its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

原始内容存档于

-0.87

 BorderRadius

-0.85

XmlAccessorType

-0.79

:✨

-0.77

 <=",

-0.75

tanleria

-0.75

stateProvider

-0.72

ValueStyle

-0.72

 engraçadas

-0.70

expandindo

-0.69

POSITIVE LOGITS

 used

1.84

 Used

1.76

Used

1.72

 USED

1.57

used

1.42

USED

1.27

 usada

1.14

 utilizado

1.07

 digunakan

1.06

 usado

1.06

Activations Density 0.164%

instances of the word "used" along with its variations in context

No Comments

No Known Activations