INDEX

Explanations

terms indicating relationships and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 تانيه

-0.78

Rüyada

-0.72

tvguidetime

-0.67

ChildScrollView

-0.67

 ویکی‌پدیا

-0.64

SOUNDBITE

-0.64

homogeneous

-0.62

 disponibilités

-0.62

ьаж

-0.60

 GeoNames

-0.59

POSITIVE LOGITS

 AttributeSet

0.59

unknownFields

0.58

sourceMap

0.53

ThemeOverlay

0.50

GMENT

0.50

 writeTo

0.48

 uwagę

0.47

 whether

0.46

serviceWorker

0.46

 TimeUnit

0.45

Activations Density 0.531%

terms indicating relationships and connections

No Comments

No Known Activations