INDEX

Explanations

instances of the word "two" 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ly

-0.98

 nemici

-0.78

 RSSSF

-0.75

 vaisselle

-0.73

ený

-0.72

er

-0.72

 ainfi

-0.71

 vectorielles

-0.71

 depositphotos

-0.71

᾿

-0.70

POSITIVE LOGITS

 CreateTagHelper

1.13

two

1.10

Two

1.06

TWO

0.99

TWO

0.99

abetes

0.93

Two

0.91

Twe

0.90

 dozen

0.88

stwo

0.86

Activations Density 0.173%

instances of the word "two" in various contexts

No Comments

No Known Activations