INDEX

Explanations

phrases related to publication details and author information

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

AddTagHelper

-0.96

coroutines

-0.69

ropriate

-0.67

цездатний

-0.66

wpi

-0.66

 GeoNames

-0.63

libft

-0.63

 autorytatywna

-0.62

SuppressMessage

-0.61

ChildScrollView

-0.61

POSITIVE LOGITS

 pleaſure

0.67

 évidence

0.60

 متعلقه

0.59

RTSC

0.55

 reaſon

0.55

 CreateTagHelper

0.52

 secular

0.50

Petit

0.50

Jîn

0.49

 Secular

0.47

Activations Density 0.428%

phrases related to publication details and author information

No Comments

No Known Activations