INDEX

Explanations

references to specific categories or identifiers

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

 tidur

-0.70

ródło

-0.67

Slf

-0.66

 اسلام

-0.62

 ладо

-0.62

 jdbcTemplate

-0.62

ribadian

-0.62

he

-0.61

adone

-0.60

dders

-0.60

POSITIVE LOGITS

 Certain

1.15

 certain

1.13

Certain

1.07

 CERTAIN

1.05

 ciertos

1.03

certain

1.01

 Certo

0.93

parsedMessage

0.88

 ciertas

0.88

 certaine

0.87

Activations Density 0.075%

references to specific categories or identifiers

No Comments

No Known Activations