INDEX

Explanations

warnings or alerts regarding safety or caution

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

uría

-0.57

 للاسماء

-0.56

痢

-0.55

estin

-0.52

大方

-0.52

 userRepository

-0.52

 عج

-0.52

 aDecoder

-0.52

ίδι

-0.51

POSITIVE LOGITS

 Warn

1.21

 alert

1.21

 warning

1.20

 warn

1.18

 alerts

1.17

 Alerts

1.14

astify

1.11

 Alert

1.07

 ALERT

1.04

 warnings

1.03

Activations Density 0.089%

warnings or alerts regarding safety or caution

No Comments

No Known Activations