INDEX

Explanations

references to meetings and discussions taking place

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

 AssemblyProduct

-0.70

Kad

-0.62

 Malay

-0.62

پرد

-0.61

ノロ

-0.61

іб

-0.60

 Yosh

-0.59

жалуйста

-0.59

 Usman

-0.58

 justicia

-0.58

POSITIVE LOGITS

 meetings

1.36

 Meetings

1.33

Meetings

1.21

 Meeting

1.20

meetings

1.18

 meeting

1.16

Meeting

1.10

meeting

1.08

 MEETING

1.06

 kasarigan

0.98

Activations Density 0.055%

references to meetings and discussions taking place

No Comments

No Known Activations