INDEX

Explanations

queries and assessments regarding value or worth

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

lineno

-0.63

出版年

-0.58

 henvisninger

-0.57

 NSCoder

-0.52

OGND

-0.51

Operands

-0.50

 σω

-0.49

 superior

-0.48

 créativité

-0.48

 Rasmus

-0.47

POSITIVE LOGITS

 amounts

0.79

 propOrder

0.78

amounts

0.74

obut

0.62

everything

0.62

ільки

0.61

 многое

0.60

bieron

0.58

 Amounts

0.57

AMOUNT

0.56

Activations Density 0.171%

queries and assessments regarding value or worth

No Comments

No Known Activations