INDEX

Explanations

phrases related to actions, particularly in conversational or narrative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

awtextra

-0.94

 transfieras

-0.78

 CreateTagHelper

-0.73

StoryboardSegue

-0.71

 purpoſe

-0.70

IonicModule

-0.69

 juſ

-0.69

Efq

-0.69

 itſelf

-0.68

sizeCache

-0.67

POSITIVE LOGITS

Lat

0.58

lat

0.57

Pyx

0.52

 okazji

0.52

aws

0.52

URLException

0.52

бы

0.51

 kell

0.51

 continu

0.51

apyrus

0.50

Activations Density 2.876%

phrases related to actions, particularly in conversational or narrative contexts

No Comments

No Known Activations