INDEX

Explanations

terms associated with qualities or characteristics 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

 JUGA

-0.49

 ddelweddau

-0.47

 lccn

-0.45

-0.42

的可

-0.42

per

-0.40

tableLayoutPanel

-0.40

[]:

-0.40

Maverick

-0.40

他不

-0.39

POSITIVE LOGITS

ViewImports

0.74

+#+#

0.73

queryInterface

0.73

>\<^

0.73

 فريبيس

0.71

^(@)

0.70

uacute

0.68

 Monfieur

0.68

ThemeOverlay

0.67

TargetException

0.67

Activations Density 0.512%

terms associated with qualities or characteristics in various contexts

No Comments

No Known Activations