INDEX

Explanations

mathematical operations and symbols in expressions

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

’

-0.75

-0.67

-0.66

</i>

-0.62

</u>

-0.58

”

-0.57

</b>

-0.57

-0.52

,”

-0.51

POSITIVE LOGITS

 plufieurs

1.07

RetentionPolicy

1.07

 ainfi

1.05

Rüyada

1.03

+#+#

1.02

ImageContext

1.00

 vectorielle

0.98

berdayakan

0.97

NUMX

0.95

 fidé

0.94

Activations Density 0.439%

mathematical operations and symbols in expressions

No Comments

No Known Activations