INDEX

Explanations

phrases indicating comparisons or conditions

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

 anaknya

-0.51

 conhece

-0.49

leva

-0.47

 متعلقه

-0.46

 तब

-0.46

 '-':

-0.43

Ӕ

-0.43

├──

-0.43

édie

-0.42

 prática

-0.42

POSITIVE LOGITS

BagLayout

0.75

styleType

0.75

HttpEntity

0.73

addCriterion

0.72

FieldBuilder

0.71

0.68

 PopupWindow

0.67

GeoNames

0.66

ällor

0.66

ⓧ

0.64

Activations Density 0.470%

phrases indicating comparisons or conditions

No Comments

No Known Activations