INDEX

Explanations

occurrences of the word "app" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

#+#

-0.84

UnusedPrivate

-0.81

 nadar

-0.75

+#+#

-0.70

↴

-0.69

ValueGenerated

-0.69

FDI

-0.68

moveToNext

-0.68

Aholisi

-0.68

ToRefresh

-0.66

POSITIVE LOGITS

app

1.63

getApp

1.43

app

1.39

APP

1.30

App

1.30

APP

1.27

App

1.26

 getApp

1.18

 appName

0.99

sApp

0.98

Activations Density 0.058%

occurrences of the word "app" in various contexts

No Comments

No Known Activations