INDEX

Explanations

references to utility functions or libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

XmlAccessType

-0.75

TypedDataSet

-0.74

StackNavigator

-0.74

 TextInputType

-0.71

HasForeignKey

-0.71

bootstrapcdn

-0.70

getColumnIndex

-0.68

&__

-0.68

accumulative

-0.68

DataMember

-0.68

POSITIVE LOGITS

util

2.90

 util

2.40

Util

2.30

 Util

2.24

UTIL

1.93

 UTIL

1.69

utili

1.39

 Utili

1.35

 utils

1.30

工具类

1.30

Activations Density 0.059%

references to utility functions or libraries

No Comments

No Known Activations