INDEX

Explanations

mentions of "information" and related terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 SEMESTER

-0.70

 suivants

-0.66

cepteur

-0.63

 abolish

-0.63

Kus

-0.62

 Caballero

-0.62

 buộc

-0.61

 التالية

-0.61

큼

-0.60

RunWith

-0.60

POSITIVE LOGITS

 information

1.84

information

1.60

 Information

1.57

Information

1.55

INFORMATION

1.54

 informations

1.45

 INFORMATION

1.44

 informa

1.29

 getInfo

1.20

 informatie

1.18

Activations Density 0.072%

mentions of "information" and related terms

No Comments

No Known Activations